© 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. 234065
    Prev
    Next
    INDEX
    Explanations

    specific technical terms

    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
    otu
    0.55
    <0xB2>
    0.48
    菓子
    0.48
    ेला
    0.47
     elementos
    0.45
    ellä
    0.45
    Р
    0.45
    ela
    0.43
    čiti
    0.42
    𝐏
    0.42
    POSITIVE LOGITS
     แนะ
    0.47
    ין
    0.46
     wsk
    0.45
     mandamus
    0.45
     bipartisan
    0.45
    FT
    0.44
    UPI
    0.43
     পা
    0.42
    ABIL
    0.42
    UIView
    0.42
    Activations Density 0.000%

    No Known Activations