© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 33254
    Prev
    Next
    INDEX
    Explanations

    Gull, Gale, Hurricane

    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
     agon
    0.44
     pik
    0.38
     endings
    0.38
    TokenType
    0.37
    conservative
    0.37
    Թ
    0.37
    الح
    0.36
    த்தான
    0.36
     cogn
    0.36
     vows
    0.35
    POSITIVE LOGITS
    風
    0.43
     틀
    0.41
     Scribner
    0.40
     바람
    0.40
     WIND
    0.39
     сила
    0.38
    力和
    0.37
    妑
    0.37
     Grupo
    0.37
     fuerza
    0.37
    Activations Density 0.002%

    No Known Activations