© 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. 2875
    Prev
    Next
    INDEX
    Explanations

    as followed by comparisons

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

    orplantsoy

    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
    وای
    0.52
    亗
    0.51
    ίων
    0.51
    MDET
    0.49
    ίου
    0.49
     peralatan
    0.48
     SLASH
    0.47
     Kuchen
    0.47
    𝜁
    0.47
     آئے
    0.47
    POSITIVE LOGITS
    ↵↵
    0.47
    resposta
    0.46
     even
    0.43
    ↵↵↵↵
    0.42
    km
    0.42
    Response
    0.41
     Comment
    0.41
    scribed
    0.41
    Places
    0.41
     prendere
    0.41
    Activations Density 0.000%

    No Known Activations