© 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. 34-GEMMASCOPE-RES-131K
    7. 78126
    Prev
    Next
    INDEX
    Explanations

    on + event names

    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
     on
    -1.16
    <bos>
    -1.14
    a
    -1.13
     каже
    -1.09
    を
    -1.02
    我们的
    -1.00
    辛い
    -0.99
    two
    -0.98
     préfère
    -0.97
     herido
    -0.94
    POSITIVE LOGITS
     behalf
    1.59
    зной
    1.07
    のですか
    1.06
     occasion
    1.02
    jetos
    1.01
    wner
    1.01
    otide
    1.01
    Demand
    1.01
     steroids
    1.00
    ৣ
    0.98
    Activations Density 0.014%

    No Known Activations