© 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. 109179
    Prev
    Next
    INDEX
    Explanations

    disorder recovery, Phoenix dating, requests pertaining

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

    code, sharks, or statistics

    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
    ﺿ
    0.50
    ש
    0.47
    NOTA
    0.47
     nared
    0.47
    AUGUST
    0.47
    ╾
    0.47
     bacterias
    0.46
    َت
    0.46
    NEUTRON
    0.46
    SERVIDOR
    0.45
    POSITIVE LOGITS
    are
    0.47
    rende
    0.45
    yl
    0.45
     élevées
    0.45
    retta
    0.45
    ate
    0.44
    rnn
    0.43
    aces
    0.43
    ă
    0.43
    essen
    0.42
    Activations Density 0.000%

    No Known Activations