© 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. 34-GEMMASCOPE-RES-131K
    7. 77255
    Prev
    Next
    INDEX
    Explanations

    as role or status

    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
     as
    -1.53
    two
    -1.50
    なども
    -1.41
     instead
    -1.39
    時的
    -1.34
    each
    -1.32
    いくつか
    -1.31
    那些
    -1.28
     and
    -1.27
    eses
    -1.24
    POSITIVE LOGITS
     a
    4.63
     an
    2.83
     part
    2.25
     the
    1.87
     both
    1.55
     follows
    1.51
     минимум
    1.39
     både
    1.34
     anjo
    1.33
     THE
    1.32
    Activations Density 0.109%

    No Known Activations