© 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. 80041
    Prev
    Next
    INDEX
    Explanations

    and you

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

    product variety; modern objectives; lights

    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
    ﯼ
    0.51
    opholes
    0.47
    第七
    0.46
    Biografia
    0.45
    ᄈ
    0.43
     secretly
    0.43
    বছ
    0.43
    ხილ
    0.43
    BankAccount
    0.42
    觴
    0.42
    POSITIVE LOGITS
     acuity
    0.46
     Primary
    0.45
    ۔
    0.43
     време
    0.42
     aiming
    0.41
     potencialmente
    0.41
     Rashford
    0.41
     তালা
    0.40
     อาท
    0.40
    in
    0.40
    Activations Density 0.002%

    No Known Activations