© 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. 94677
    Prev
    Next
    INDEX
    Explanations

    brand, County, following

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

    explaining different approaches

    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
    ط
    0.59
    ⵚ
    0.52
     polémica
    0.50
    ⵙ
    0.49
     solicitado
    0.49
     kaynağından
    0.49
    انگ
    0.49
     sistemat
    0.47
    طيني
    0.47
    ۤ
    0.46
    POSITIVE LOGITS
    ']:
    0.46
    bler
    0.46
    AT
    0.44
    ridge
    0.44
    ow
    0.43
    rs
    0.43
     experi
    0.42
     गौ
    0.42
    msg
    0.41
    ry
    0.41
    Activations Density 0.000%

    No Known Activations