© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101487
    Prev
    Next
    INDEX
    Explanations

    operands, arguments, factors, reactants

    np_acts-logits-general · gemini-2.5-flash-lite

    function or method parameters and arguments.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    the word "operand" or "operands" in technical programming and mathematical contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -2.55
    f
    -2.00
    ):
    -1.79
    or
    -1.79
     –
    -1.77
    1
    -1.67
    }$
    -1.67
    ”:
    -1.66
    ":
    -1.58
     still
    -1.52
    POSITIVE LOGITS
    翆
    2.38
    ৄ
    1.99
    UrlEncoded
    1.98
    𓆝
    1.96
    
    1.95
    Privatpatient
    1.95
    ৢ
    1.91
    IRST
    1.88
    珦
    1.88
    JEAN
    1.83
    Activations Density 0.026%

    No Known Activations