© 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. 75278
    Prev
    Next
    INDEX
    Explanations

    political speech and criticism

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

    desire, sexuality, and code

    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
    strom
    0.48
    constitutional
    0.46
    BuildConfig
    0.44
    Ро
    0.42
    erunner
    0.42
     الأمن
    0.41
    regulating
    0.40
    쥐
    0.38
    stainless
    0.38
    ept
    0.38
    POSITIVE LOGITS
     Sand
    0.47
     desire
    0.45
     sand
    0.44
     修
    0.44
     किराया
    0.44
     "/"
    0.43
     使用
    0.43
     沙
    0.43
     suv
    0.42
     hitbox
    0.42
    Activations Density 0.000%

    No Known Activations