© 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. 131426
    Prev
    Next
    INDEX
    Explanations

    trademark symbols

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

    buy, consent, C, copied down

    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
     AFRICA
    0.46
    бир
    0.45
    ợp
    0.39
     оголо
    0.39
    旄
    0.39
    াপুর
    0.39
    ᆸ
    0.39
     балан
    0.38
    志森
    0.38
     BALANCE
    0.38
    POSITIVE LOGITS
    ®.
    0.57
    ™.
    0.48
    ®
    0.46
     seedling
    0.45
     pertama
    0.44
     unidades
    0.44
     centrifugation
    0.43
     tertinggi
    0.43
     units
    0.43
    ™
    0.42
    Activations Density 0.000%

    No Known Activations