© 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. 155784
    Prev
    Next
    INDEX
    Explanations

    industry storage plans

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

    pointers, integrates, check

    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
     エネルギー
    0.56
    팎
    0.52
    pm
    0.50
     熱
    0.48
     febbraio
    0.46
     金属
    0.44
     детям
    0.44
    ㅈ
    0.43
     infancia
    0.43
     便
    0.43
    POSITIVE LOGITS
    خ
    0.51
    Gorgeous
    0.48
    嗥
    0.46
     kolor
    0.45
    ทำ
    0.45
    Presented
    0.45
    Hou
    0.45
     الل
    0.44
     بُ
    0.44
    看上去
    0.43
    Activations Density 0.001%

    No Known Activations