© 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. 131686
    Prev
    Next
    INDEX
    Explanations

    special session

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

    of questions

    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
    部の
    0.50
    garia
    0.49
    ために
    0.48
    sbParams
    0.47
    龴
    0.47
    બ્
    0.46
    ̑
    0.46
    🌃
    0.45
     робо
    0.45
     vattati
    0.45
    POSITIVE LOGITS
     Nummer
    0.55
     a
    0.54
     nummer
    0.50
     Tast
    0.48
     sequent
    0.45
     orth
    0.45
     Niels
    0.45
    of
    0.44
     Mise
    0.44
     Number
    0.44
    Activations Density 0.002%

    No Known Activations