© 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. 217725
    Prev
    Next
    INDEX
    Explanations

    site information

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

    keys, Liam, EIN, social, non-English

    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
     sniffing
    0.50
     triggers
    0.49
    onies
    0.46
    Pressed
    0.46
    𝙍
    0.46
    \
    0.46
     pickles
    0.46
    葫
    0.45
    Beach
    0.45
     estás
    0.45
    POSITIVE LOGITS
    脳
    0.48
     která
    0.45
    ಙ
    0.44
     która
    0.43
     deren
    0.43
     worn
    0.42
    入門
    0.42
     aceea
    0.42
     terza
    0.42
     STUDY
    0.42
    Activations Density 0.000%

    No Known Activations