© 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. 237512
    Prev
    Next
    INDEX
    Explanations

    Injury to deliver

    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
    ⟹
    0.55
    ্বাস
    0.51
    ENSITY
    0.50
     పరుగులు
    0.49
    ㅀ
    0.49
    ⌵
    0.49
    acious
    0.47
    état
    0.47
    ъем
    0.46
     టెస్
    0.45
    POSITIVE LOGITS
     traged
    0.45
     are
    0.44
    勲
    0.43
     peeling
    0.42
    II
    0.40
     mê
    0.39
     peel
    0.39
     molte
    0.39
     HB
    0.38
     Covid
    0.38
    Activations Density 0.002%

    No Known Activations