© 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. 155085
    Prev
    Next
    INDEX
    Explanations

    OEM parts

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

    harmful language or killing

    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
    Rita
    0.49
    (
    0.49
    مع
    0.49
    Sharma
    0.47
     rehabilitated
    0.46
    Michael
    0.46
    Vijay
    0.45
     ***
    0.45
    س
    0.45
    ***
    0.44
    POSITIVE LOGITS
     PLASMA
    0.59
    ʏ
    0.50
     interesar
    0.49
     उसी
    0.48
     atthakath
    0.48
     कॉस
    0.48
     fruto
    0.46
     SIINFEKL
    0.46
     amm
    0.46
    plasma
    0.45
    Activations Density 0.000%

    No Known Activations