© 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. 65277
    Prev
    Next
    INDEX
    Explanations

    be to vast availability of dream

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

    identifying specific segments or signals

    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
    aj
    0.50
     получать
    0.47
     deleg
    0.46
     घटा
    0.46
     벨
    0.43
     gypsum
    0.42
     아직
    0.42
     modulus
    0.41
     ベルト
    0.41
    リ
    0.41
    POSITIVE LOGITS
     جوړونکو
    0.46
    जम्मू
    0.46
    ἢ
    0.43
    enuine
    0.42
     Spacious
    0.41
    كمان
    0.41
     khe
    0.40
    getStudentNo
    0.40
     configuração
    0.40
    amless
    0.40
    Activations Density 0.000%

    No Known Activations