© 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. 2069
    Prev
    Next
    INDEX
    Explanations

    technical formatting and code

    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
    <unused544>
    0.58
    squarePos
    0.55
    <unused609>
    0.55
    𝚋
    0.54
    <unused291>
    0.52
    <unused301>
    0.52
    <unused657>
    0.52
    𒋼
    0.52
    <unused192>
    0.52
    <unused2013>
    0.51
    POSITIVE LOGITS
    0.58
     guide
    0.51
     medical
    0.48
     light
    0.48
    ,
    0.47
     power
    0.46
     continuum
    0.45
    /
    0.45
     wilderness
    0.44
     history
    0.44
    Activations Density 0.000%

    No Known Activations