© 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. 184624
    Prev
    Next
    INDEX
    Explanations

    permit if road

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

    specific articles or show notes

    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
    鼓励
    0.46
     encouragement
    0.41
    高效
    0.40
    제로
    0.40
    邱
    0.40
     quatre
    0.39
    一生
    0.39
    زين
    0.39
    вят
    0.39
    蔚
    0.39
    POSITIVE LOGITS
    াতাড়ি
    0.52
    ামো
    0.50
     operazioni
    0.49
    髏
    0.48
    supset
    0.47
    埚
    0.46
     worsened
    0.46
    కంగా
    0.45
    atorias
    0.45
     マスター
    0.44
    Activations Density 0.001%

    No Known Activations