© 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. 36268
    Prev
    Next
    INDEX
    Explanations

    sesame and rather than

    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
    chetto
    0.45
    readystatechange
    0.39
     رمی
    0.39
    ங்கை
    0.38
    ==-
    0.38
    ్యాన్ని
    0.38
    hena
    0.37
    仴
    0.37
    ფორმა
    0.37
    hun
    0.36
    POSITIVE LOGITS
     cost
    0.41
     nove
    0.41
     compression
    0.40
     tapi
    0.40
     repell
    0.40
     давно
    0.40
     mentre
    0.39
     compressor
    0.39
     weed
    0.38
     shed
    0.38
    Activations Density 0.000%

    No Known Activations