© 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. 5319
    Prev
    Next
    INDEX
    Explanations

    others, other languages, also

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

    inspiring creative aspirational

    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
    0.41
     questo
    0.39
     Tuttavia
    0.36
     هذا
    0.35
    ـــ
    0.34
    Example
    0.34
     acest
    0.33
    .
    0.33
     erstes
    0.32
     azonban
    0.32
    POSITIVE LOGITS
     другие
    0.40
     अन्य
    0.39
     інших
    0.38
     также
    0.38
     altres
    0.38
     других
    0.37
    อื่นๆ
    0.36
    そもそも
    0.36
     다른
    0.35
     ასევე
    0.35
    Activations Density 0.998%

    No Known Activations