© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3805
    Prev
    Next
    INDEX
    Explanations

    numbers with currency and percentage units

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

    numbers followed by scale words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Notepad
    0.34
    玠
    0.34
     Marker
    0.33
     Möglichkeit
    0.33
     Espresso
    0.32
     Activation
    0.32
    溦
    0.32
     تعالیٰ
    0.32
     Geschwindigkeit
    0.32
     Controle
    0.31
    POSITIVE LOGITS
     (!)
    0.35
    reported
    0.35
     млн
    0.33
    ́
    0.31
    اديم
    0.31
    legisl
    0.31
    three
    0.31
     totaled
    0.30
    (!)
    0.30
    seven
    0.29
    Activations Density 0.267%

    No Known Activations