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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 89689
    Prev
    Next
    INDEX
    Explanations

    variable assignments or equalities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     why
    -0.92
     resources
    -0.85
     something
    -0.85
     of
    -0.84
    onsor
    -0.83
     bomberos
    -0.83
     patterns
    -0.83
    partir
    -0.83
     Why
    -0.82
    share
    -0.82
    POSITIVE LOGITS
    }=$
    2.45
     =
    2.36
    )=$
    2.08
    }}=$
    1.89
     $=$
    1.70
    ]=$
    1.51
     это
    1.49
    =$
    1.21
    =
    1.18
     =\
    1.16
    Activations Density 0.019%

    No Known Activations