© 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. 112564
    Prev
    Next
    INDEX
    Explanations

    raspberry shade, life time opportunity

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

    positive affirmations for ideas

    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
    0
    0.48
    uc
    0.47
    বি
    0.45
    İZ
    0.45
    َ
    0.44
    يع
    0.44
    2
    0.44
    بي
    0.43
     administered
    0.43
    lac
    0.43
    POSITIVE LOGITS
     विनाश
    0.62
     metamorphosis
    0.58
    attha
    0.55
     camas
    0.53
     絶対
    0.53
     destru
    0.52
     currant
    0.52
     hedon
    0.52
     flee
    0.51
     satan
    0.50
    Activations Density 0.000%

    No Known Activations