© 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. 168359
    Prev
    Next
    INDEX
    Explanations

    flip sandwich

    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
     throw
    0.40
     ROM
    0.39
     Unterstüt
    0.38
     තා
    0.38
     Hyp
    0.38
    Argentina
    0.38
     Adjusted
    0.37
    锢
    0.37
     termin
    0.37
     Heinz
    0.37
    POSITIVE LOGITS
     Representatives
    0.39
     représentants
    0.37
    Representatives
    0.37
     Ejemplo
    0.36
     représentent
    0.36
     redness
    0.35
    ாள
    0.35
    Ej
    0.34
     multitudes
    0.34
     अराज
    0.34
    Activations Density 0.000%

    No Known Activations