© 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. 12527
    Prev
    Next
    INDEX
    Explanations

    GitHub repository file paths

    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
     piet
    0.38
    midi
    0.37
    теля
    0.36
     mực
    0.36
    ilor
    0.36
     //.
    0.35
    adus
    0.35
    radi
    0.35
    éclair
    0.35
     nors
    0.35
    POSITIVE LOGITS
     overview
    0.47
     About
    0.45
     FAQ
    0.44
     Overview
    0.44
     blob
    0.42
     roadmap
    0.42
     블
    0.41
     News
    0.41
     article
    0.40
    blob
    0.40
    Activations Density 0.007%

    No Known Activations