© 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. 183840
    Prev
    Next
    INDEX
    Explanations

    formal information and permissions

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

    pressure for, predicting, creature, debate

    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
    .+\
    0.50
     проце
    0.47
    ...+
    0.46
    ronaut
    0.44
    プロセス
    0.42
    。...
    0.42
    手順
    0.41
    esthetics
    0.41
    anay
    0.41
    ighted
    0.40
    POSITIVE LOGITS
     V
    0.54
     mV
    0.50
    见的
    0.49
     notably
    0.49
     části
    0.47
     első
    0.45
     discuss
    0.45
    ڨ
    0.44
     quint
    0.44
     eggplant
    0.44
    Activations Density 0.001%

    No Known Activations