© 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. 105598
    Prev
    Next
    INDEX
    Explanations

    parts of things

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

    boolean logic conditions

    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
    moh
    0.54
    وس
    0.53
    ना
    0.52
    na
    0.52
    me
    0.51
    men
    0.51
    콜
    0.50
    sunset
    0.49
    на
    0.48
    ком
    0.48
    POSITIVE LOGITS
     міста
    0.50
    л
    0.45
     virkelig
    0.45
     Midway
    0.44
     l
    0.43
     villes
    0.43
     рассматри
    0.42
     tions
    0.42
     обслуживания
    0.42
     vượt
    0.42
    Activations Density 0.000%

    No Known Activations