© 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. 189063
    Prev
    Next
    INDEX
    Explanations

    global institutions, four respondents

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

    confirm, usually, or model names

    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
    パラ
    0.53
     season
    0.53
    季
    0.52
     smugglers
    0.52
     sorpre
    0.51
    種類の
    0.50
     smugg
    0.50
     Season
    0.49
     SEASON
    0.49
     unsus
    0.48
    POSITIVE LOGITS
     hogar
    0.46
    face
    0.45
    oeuvre
    0.45
    erView
    0.44
    immersive
    0.43
    endpoint
    0.43
    ises
    0.42
    ة
    0.42
    ace
    0.42
     آثار
    0.42
    Activations Density 0.001%

    No Known Activations