© 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. 48493
    Prev
    Next
    INDEX
    Explanations

    words preceding various topics

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

    couldinstantly, couldexperience, couldanalyze

    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
    Tema
    0.53
    bě
    0.52
    ült
    0.49
    一
    0.48
    тно
    0.46
     evita
    0.46
    <0x9A>
    0.45
    ⵓ
    0.45
    فك
    0.45
    Farmer
    0.44
    POSITIVE LOGITS
     쓰고
    0.48
     ফুল
    0.43
     ជា
    0.43
     ដែល
    0.41
     dropout
    0.40
     하며
    0.40
    することができる
    0.39
     hypersonic
    0.39
     정상
    0.39
    icially
    0.39
    Activations Density 0.000%

    No Known Activations