© 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. 42237
    Prev
    Next
    INDEX
    Explanations

    was the

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

    hygiene and cleanliness

    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
     capitalization
    0.52
     socialization
    0.48
     laborers
    0.46
     DIY
    0.43
     fruitless
    0.42
     lifestyles
    0.41
    ሩ
    0.41
     бизне
    0.41
     فائ
    0.40
    फट
    0.39
    POSITIVE LOGITS
     was
    0.50
    었고
    0.46
     hitbox
    0.46
    ífico
    0.43
    úncia
    0.43
    odesmium
    0.42
    %，
    0.42
    refs
    0.42
     現在
    0.42
    endment
    0.42
    Activations Density 0.000%

    No Known Activations