© 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. 137111
    Prev
    Next
    INDEX
    Explanations

    scientific, technical terms

    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
    ContentView
    0.37
     ännu
    0.37
     }}\
    0.37
     бө
    0.36
    дово
    0.35
    嶇
    0.35
    лое
    0.35
     عادت
    0.35
     τὸν
    0.35
     pelajar
    0.35
    POSITIVE LOGITS
    ich
    0.41
    RICT
    0.38
    Emp
    0.37
    .$(
    0.37
    emp
    0.37
    cons
    0.36
     sciences
    0.36
    Cons
    0.36
    Sciences
    0.36
    ab
    0.36
    Activations Density 0.001%

    No Known Activations