© 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. 39412
    Prev
    Next
    INDEX
    Explanations

    foreign punctuation or accents

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

    probabilistic outcomes or specific scenarios

    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
     ince
    0.49
     یا
    0.48
    که
    0.46
     that
    0.45
    یم
    0.45
    וק
    0.45
     morning
    0.45
    ד
    0.45
     eyep
    0.44
     analysis
    0.43
    POSITIVE LOGITS
    versammlung
    0.52
    tsz
    0.46
    éraires
    0.45
    మణ
    0.45
     exquis
    0.44
    kä
    0.44
    ेशंस
    0.44
    lü
    0.43
    kari
    0.43
     Honduras
    0.42
    Activations Density 0.000%

    No Known Activations