© 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. 244363
    Prev
    Next
    INDEX
    Explanations

    prepaid card

    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
     Programmer
    0.49
     Discovery
    0.45
    傷
    0.44
    istungen
    0.43
     Suprem
    0.43
     rekord
    0.42
    ал
    0.42
     pesos
    0.42
    城
    0.42
    ழை
    0.42
    POSITIVE LOGITS
     varietà
    0.58
     покупать
    0.48
    ność
    0.48
     purity
    0.48
    UiThread
    0.48
     дает
    0.48
     কিনতে
    0.48
     หา
    0.48
    ebut
    0.47
     আজকে
    0.47
    Activations Density 0.001%

    No Known Activations