© 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. 90201
    Prev
    Next
    INDEX
    Explanations

    book, sole, third, one, before

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

    early warning

    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
    𝖐
    0.53
    ishma
    0.52
    ри
    0.50
    ೧
    0.48
     políticos
    0.48
     compradores
    0.46
     інших
    0.46
     ګرځنده
    0.46
     ఆదేశ
    0.45
    ↖
    0.45
    POSITIVE LOGITS
    tt
    0.48
     Blow
    0.45
    Duncan
    0.44
     Glo
    0.44
    tops
    0.44
     பொருந்த
    0.43
     Mark
    0.43
    مار
    0.43
    Glass
    0.43
     Duncan
    0.42
    Activations Density 0.000%

    No Known Activations