© 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. 111827
    Prev
    Next
    INDEX
    Explanations

    cellular radio

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

    alternative wording and structure

    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
    f
    0.51
    eg
    0.50
    ln
    0.47
    user
    0.46
    [\
    0.46
    на
    0.46
    banner
    0.46
    benef
    0.45
    $$\
    0.45
    inyl
    0.45
    POSITIVE LOGITS
    وقف
    0.48
    的感觉
    0.46
    شاہ
    0.45
    تباينه
    0.45
     jwt
    0.45
     probabilities
    0.43
    WithMessage
    0.43
     candidacy
    0.43
     statistiques
    0.43
    ъм
    0.43
    Activations Density 0.000%

    No Known Activations