© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71421
    Prev
    Next
    INDEX
    Explanations

    specific entities and compound words

    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_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
    ㎡
    -1.15
     from
    -1.05
    afterEach
    -1.04
    `),
    -1.00
     &___
    -1.00
    öbb
    -0.99
    :+:
    -0.96
     endforeach
    -0.95
    }")]
    -0.95
     our
    -0.94
    POSITIVE LOGITS
    9
    1.03
    がとても
    1.01
    poisson
    1.00
     других
    0.93
    It
    0.89
    tries
    0.88
    あー
    0.87
     considérons
    0.86
     wygląda
    0.84
    そも
    0.84
    Activations Density 0.003%

    No Known Activations