© 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. 24337
    Prev
    Next
    INDEX
    Explanations

    Elektrobit, Kapwing, trakt-scrobbler

    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
    idente
    0.49
    ellery
    0.46
    uyentes
    0.42
     contrary
    0.41
     utilising
    0.41
    ulière
    0.40
     Projeto
    0.40
    墅
    0.39
     Seguro
    0.39
    oured
    0.39
    POSITIVE LOGITS
    ka
    0.54
    nik
    0.50
    ku
    0.50
    ków
    0.50
    ki
    0.49
    kar
    0.49
    tv
    0.49
    klus
    0.46
     telewiz
    0.46
    ik
    0.45
    Activations Density 0.009%

    No Known Activations