© 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. 240173
    Prev
    Next
    INDEX
    Explanations

    co-creator’ of a local

    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
    퐫
    0.50
    
    0.48
    ᵛ
    0.48
    ού
    0.47
    ɮ
    0.46
    on
    0.46
    所有
    0.46
    𝒐
    0.46
     புதிய
    0.46
    новый
    0.46
    POSITIVE LOGITS
     en
    0.46
     reco
    0.44
     auditor
    0.44
     rewind
    0.44
     dancers
    0.43
    Cris
    0.43
     men
    0.43
    :
    0.43
     him
    0.42
     Auditor
    0.42
    Activations Density 0.000%

    No Known Activations