© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 111574
    Prev
    Next
    INDEX
    Explanations

    years, old, p.m

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

    Forget hand-holding

    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
    ↵
    0.54
     Berm
    0.49
    >
    0.46
    \
    0.45
     Parisian
    0.42
     Adolf
    0.41
     
    0.40
     Denis
    0.39
    –
    0.39
    ۱
    0.39
    POSITIVE LOGITS
    KSprite
    0.51
    距離
    0.50
    এশিয়া
    0.49
     重量
    0.49
    чила
    0.47
     軽量
    0.46
    স্তাফ
    0.46
    重量
    0.46
     prothorace
    0.45
     інших
    0.45
    Activations Density 0.002%

    No Known Activations