© 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. 133067
    Prev
    Next
    INDEX
    Explanations

    Google services and Android versions

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

    code generation and explanations

    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
     ),
    0.50
    サラダ
    0.46
     كن
    0.44
     trois
    0.42
    洺
    0.42
    Decorator
    0.42
     pistola
    0.42
     o
    0.41
     android
    0.41
     insensitive
    0.41
    POSITIVE LOGITS
    க
    0.52
    igious
    0.52
    хе
    0.52
     Lakh
    0.51
    핳
    0.51
    শুভ
    0.50
     கேள்
    0.50
    चि
    0.49
    ори
    0.49
    новь
    0.48
    Activations Density 0.000%

    No Known Activations