© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 16108
    Prev
    Next
    INDEX
    Explanations

    early lesions during carcinogenesis

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

    The neuron identifies content related to entertainment news and TV productions, particularly focusing on actor and show names.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     tromper
    -1.12
    出场
    -0.99
    ♿
    -0.99
    ἢ
    -0.98
     chrétien
    -0.97
     température
    -0.96
    蹣
    -0.96
     famosas
    -0.95
    Или
    -0.95
     malades
    -0.95
    POSITIVE LOGITS
     and
    1.38
    1.03
    1.02
     crescente
    0.99
    0.97
     have
    0.96
     jesteśmy
    0.96
    }(),
    0.95
    
    0.95
    ṓ
    0.93
    Activations Density 0.002%

    No Known Activations