© 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. 174137
    Prev
    Next
    INDEX
    Explanations

    guess or speculation

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

    personal connection and common observations

    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
     ativos
    0.54
    ATIVA
    0.53
    𝙎
    0.53
    وت
    0.52
    ات
    0.50
    مد
    0.49
     triángulos
    0.49
    تور
    0.48
    隧道
    0.48
    強制
    0.47
    POSITIVE LOGITS
     guesses
    0.48
     եր
    0.48
     guessed
    0.47
     preview
    0.47
     a
    0.47
     guess
    0.46
    am
    0.44
     conce
    0.44
    em
    0.43
     speculated
    0.42
    Activations Density 0.000%

    No Known Activations