© 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. 128459
    Prev
    Next
    INDEX
    Explanations

    technical terms or instructions

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

    mathematical or code related terms

    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
    ImageIcon
    0.46
    También
    0.45
    imagen
    0.43
    ц
    0.43
    eseen
    0.43
    ך
    0.42
    它
    0.42
    eye
    0.41
    ischer
    0.41
    רא
    0.41
    POSITIVE LOGITS
     grossesse
    0.47
     μο
    0.43
     mãos
    0.42
     întâ
    0.42
     ε
    0.42
     proté
    0.41
     précip
    0.41
    ెక్టర్
    0.40
     rét
    0.40
     délais
    0.40
    Activations Density 0.000%

    No Known Activations