© 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. 127674
    Prev
    Next
    INDEX
    Explanations

    cleaning benefits, reduction per person

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

    malware developers study enough additional

    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
    0.55
     della
    0.49
    Throw
    0.48
     Apple
    0.48
     แก
    0.48
     Microphone
    0.48
    <strong>
    0.47
     Accessories
    0.47
     Corrections
    0.47
     MAN
    0.47
    POSITIVE LOGITS
    حمد
    0.45
    *=
    0.44
    чайно
    0.44
    nationality
    0.43
    ем
    0.43
    protection
    0.43
    роид
    0.43
    conexion
    0.43
    езде
    0.42
    pract
    0.42
    Activations Density 0.000%

    No Known Activations