© 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. 231405
    Prev
    Next
    INDEX
    Explanations

    cutting or inflicting costs

    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
    p
    0.50
     SOME
    0.50
     some
    0.49
     titles
    0.48
     n
    0.47
     single
    0.47
    g
    0.47
     ga
    0.46
     eden
    0.46
    x
    0.46
    POSITIVE LOGITS
    حصل
    0.50
    ي
    0.50
    Cut
    0.47
     inflicted
    0.46
     Médico
    0.46
    баров
    0.46
    醫生
    0.46
    Нау
    0.45
     Música
    0.45
    🍸
    0.45
    Activations Density 0.000%

    No Known Activations