© 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. 122336
    Prev
    Next
    INDEX
    Explanations

    specific concepts with context

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

    intent parsing and classification

    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
     S
    0.53
     R
    0.46
     B
    0.45
     J
    0.44
     K
    0.42
     T
    0.40
     M
    0.40
     N
    0.40
     sciences
    0.40
     Ch
    0.40
    POSITIVE LOGITS
    ៥
    0.40
    ៣
    0.40
    hearted
    0.39
    amacare
    0.38
     финансо
    0.38
    ulently
    0.37
     хотят
    0.37
    嚷
    0.37
    hentication
    0.36
    porcion
    0.36
    Activations Density 0.000%

    No Known Activations