© 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. 20526
    Prev
    Next
    INDEX
    Explanations

    ) – prefix

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

    please provide the text you want

    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
    áját
    0.44
    mathrm
    0.43
     diarios
    0.42
    вший
    0.42
    бл
    0.42
     мла
    0.42
     ज़िन्दगी
    0.40
    }\!\
    0.40
    逾
    0.40
     uczni
    0.40
    POSITIVE LOGITS
    rescue
    0.53
    can
    0.50
    amera
    0.48
    are
    0.48
    ardier
    0.45
    arm
    0.44
    hem
    0.44
    showthread
    0.44
    outil
    0.43
    oblig
    0.43
    Activations Density 0.000%

    No Known Activations