© 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. 53-GEMMASCOPE-2-RES-262K
    7. 86326
    Prev
    Next
    INDEX
    Explanations

    Collecting indices

    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_53_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
    println
    0.44
    routerProps
    0.42
    Struct
    0.41
    zyst
    0.40
    BeforeCall
    0.39
     Convent
    0.39
     Prague
    0.38
    <()>
    0.38
    crate
    0.38
    bant
    0.38
    POSITIVE LOGITS
     Vec
    0.68
    vec
    0.63
    Vec
    0.61
     vec
    0.59
     caps
    0.41
     drained
    0.41
     drain
    0.41
     hev
    0.40
    VAC
    0.40
     draining
    0.40
    Activations Density 0.020%

    No Known Activations