© 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. 40-GEMMASCOPE-2-RES-262K
    7. 135923
    Prev
    Next
    INDEX
    Explanations

    beyond passive reading

    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_40_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
    চালক
    0.41
    alop
    0.41
     जला
    0.40
    getAs
    0.39
    χαν
    0.38
    instag
    0.38
    வுகளில்
    0.38
    ᵁ
    0.37
     glau
    0.37
     지도
    0.37
    POSITIVE LOGITS
    Bubble
    0.38
     മുഴ
    0.38
     यू
    0.36
    omer
    0.36
     Bubble
    0.36
    @
    0.36
    bindings
    0.36
    瞩
    0.36
     легче
    0.35
    덬
    0.35
    Activations Density 0.001%

    No Known Activations