© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127719
    Prev
    Next
    INDEX
    Explanations

    technical terms and procedures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused2140>
    0.57
     ದು
    0.52
     upsets
    0.52
     preds
    0.51
     главного
    0.51
    唥
    0.50
     infringing
    0.50
     predom
    0.50
     Vertrags
    0.50
     infil
    0.50
    POSITIVE LOGITS
    Coordinates
    0.47
    作为
    0.45
    email
    0.44
    一
    0.44
    ها
    0.43
    onać
    0.40
    ier
    0.40
    نق
    0.40
    ort
    0.39
    NE
    0.39
    Activations Density 0.000%

    No Known Activations