© 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. 124292
    Prev
    Next
    INDEX
    Explanations

    warranty service

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

    model something

    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
    рец
    0.49
     Molding
    0.49
    െ
    0.47
    연
    0.47
     Materialien
    0.46
    নির্বাচ
    0.45
    砊
    0.45
     Examiner
    0.44
    емые
    0.44
     Vault
    0.43
    POSITIVE LOGITS
     γ
    0.60
    غراف
    0.49
     لا
    0.47
     LGBT
    0.47
    γου
    0.46
     SEASON
    0.46
     θ
    0.45
     مصرف
    0.44
     hippie
    0.44
     η
    0.44
    Activations Density 0.000%

    No Known Activations