© 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. 148925
    Prev
    Next
    INDEX
    Explanations

    parliamentary procedure

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

    avoiding negative consequences

    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
     to
    0.50
    Ű
    0.49
    8
    0.46
    成都
    0.46
     AMAZING
    0.45
    ★
    0.45
    STAN
    0.44
    ¿
    0.43
     Training
    0.43
     Cube
    0.43
    POSITIVE LOGITS
    闱
    0.57
    𝔂
    0.52
    ව්
    0.48
    յան
    0.47
    𝚞
    0.47
     մ
    0.46
    ന്‍സ്
    0.46
    variance
    0.46
     trembling
    0.46
     بابەت
    0.46
    Activations Density 0.001%

    No Known Activations