© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 164889
    Prev
    Next
    INDEX
    Explanations

    expressive compliments

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

    spending tons of time

    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
    MUN
    0.46
    Ž
    0.45
     unbalanced
    0.44
    䍧
    0.44
    의
    0.43
    र्ती
    0.43
    vestre
    0.43
    서는
    0.42
    Toplam
    0.42
    anted
    0.42
    POSITIVE LOGITS
     publicit
    0.52
     poesia
    0.47
    സിക
    0.46
    いただけます
    0.45
    工商
    0.44
    铺
    0.44
     tinta
    0.43
     Needle
    0.43
    美术
    0.43
     idioms
    0.43
    Activations Density 0.000%

    No Known Activations