© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199337
    Prev
    Next
    INDEX
    Explanations

    years since

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

    understand how

    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
    штейн
    0.45
    ке
    0.45
    ку
    0.43
    كم
    0.42
    Z
    0.42
     Indore
    0.42
    one
    0.41
    ij
    0.41
    кара
    0.40
    mout
    0.40
    POSITIVE LOGITS
     {}>,
    0.48
    NETT
    0.46
    রদ্ব
    0.46
    र्डर
    0.45
    CAL
    0.45
     Interface
    0.45
    CALL
    0.44
    وامی
    0.44
     Leasing
    0.44
    িত্তিক
    0.43
    Activations Density 0.000%

    No Known Activations