© 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. 134215
    Prev
    Next
    INDEX
    Explanations

    vintage clothing

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

    address on, SMB traffic, hunted by, absorbed during, comes back

    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
    쑤
    0.50
     сфере
    0.47
     तुमच्या
    0.45
    Ⴎ
    0.45
     sorpresa
    0.45
     كتبت
    0.45
     ইংরে
    0.44
    ુભ
    0.44
     menulis
    0.44
     siguiendo
    0.43
    POSITIVE LOGITS
     imped
    0.55
    vær
    0.48
    k
    0.46
    j
    0.46
    ilk
    0.45
    går
    0.45
     możliwość
    0.44
    g
    0.43
    ilaire
    0.42
    vě
    0.42
    Activations Density 0.001%

    No Known Activations