© 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. 115032
    Prev
    Next
    INDEX
    Explanations

    words followed by common continuations

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

    but considered required

    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
     통해
    0.58
     우
    0.52
     വ്യക്തി
    0.51
    posizione
    0.51
    ließt
    0.50
     상대
    0.50
     케
    0.49
     বাড়ছে
    0.49
     улицы
    0.49
    ς
    0.49
    POSITIVE LOGITS
    |
    0.47
    ذكر
    0.46
     taps
    0.46
    หนัก
    0.44
     or
    0.43
    ^{\
    0.43
     enlisted
    0.42
    ¹
    0.42
     traps
    0.42
    امد
    0.42
    Activations Density 0.001%

    No Known Activations