© 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. 174084
    Prev
    Next
    INDEX
    Explanations

    security not guaranteed

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

    common words followed by other common words

    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
     եր
    0.46
     giornal
    0.46
     आणखी
    0.43
     ಮಾ
    0.42
    °)
    0.41
     來
    0.41
     మార్
    0.41
    रों
    0.40
     saludar
    0.40
     అ
    0.40
    POSITIVE LOGITS
    IT
    0.48
    E
    0.45
     Jok
    0.43
    QM
    0.42
    N
    0.42
    in
    0.42
    HQ
    0.41
    er
    0.41
    keit
    0.40
     Nylon
    0.40
    Activations Density 0.000%

    No Known Activations