© 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. 131438
    Prev
    Next
    INDEX
    Explanations

    flex: 1

    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
     finais
    0.43
     finals
    0.40
     Finals
    0.40
    佅
    0.39
    串
    0.38
     zeich
    0.37
     ঘ
    0.37
     finales
    0.36
    FontFace
    0.36
     paréntesis
    0.36
    POSITIVE LOGITS
    oplast
    0.40
    翦
    0.40
    thank
    0.38
     Adverse
    0.38
     распространен
    0.38
    enn
    0.37
    omer
    0.37
    uen
    0.36
    ठन
    0.36
     घटा
    0.36
    Activations Density 0.001%

    No Known Activations