© 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. 15495
    Prev
    Next
    INDEX
    Explanations

    sentence starts or questions

    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
     большинство
    -1.30
     poë
    -1.24
    basically
    -1.20
     of
    -1.16
     migliori
    -1.15
     considère
    -1.15
     indien
    -1.14
    鰯
    -1.13
    Basically
    -1.13
    owing
    -1.13
    POSITIVE LOGITS
    OOTDTY
    1.16
     now
    1.14
     mauvaise
    1.12
    Ausstattung
    1.12
     maybe
    1.12
    开始
    1.09
     perhaps
    1.07
    zené
    1.05
    ではなく
    1.05
    Hersteller
    1.03
    Activations Density 0.015%

    No Known Activations