© 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. 121935
    Prev
    Next
    INDEX
    Explanations

    first resolution

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

    cases

    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
    νων
    0.55
    ს
    0.54
     réactions
    0.53
    い
    0.51
    ʢ
    0.51
    வதற்காக
    0.49
    を務
    0.48
    وا
    0.48
    ίζουν
    0.48
    جموعة
    0.48
    POSITIVE LOGITS
    ales
    0.48
     wiss
    0.47
     nd
    0.46
     あり
    0.46
     rs
    0.45
     rm
    0.45
     ata
    0.45
    0
    0.45
     own
    0.45
     ”.
    0.44
    Activations Density 0.000%

    No Known Activations