© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 57294
    Prev
    Next
    INDEX
    Explanations

    This is a sentence starter

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

    declining problematic requests

    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
    ibel
    0.46
     стари
    0.44
    豕
    0.44
    说到
    0.44
    ché
    0.43
     mentioned
    0.42
    コロ
    0.40
     картину
    0.40
    ק
    0.40
     Schwer
    0.39
    POSITIVE LOGITS
     demonstrates
    0.57
     constitutes
    0.48
     ensures
    0.47
     فیصلے
    0.47
     helps
    0.46
     representa
    0.46
     strengthens
    0.46
     represents
    0.45
     initi
    0.45
     rappresenta
    0.44
    Activations Density 0.030%

    No Known Activations