© 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. 31-GEMMASCOPE-2-RES-262K
    7. 21090
    Prev
    Next
    INDEX
    Explanations

    not a, now, sad, enjoy

    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_31_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
    も
    0.54
    도
    0.52
    곰
    0.50
    heating
    0.46
    🄴
    0.45
    绽
    0.44
    ન
    0.44
    NU
    0.43
    ਨ
    0.43
    炭
    0.43
    POSITIVE LOGITS
    ibut
    0.49
    bollywood
    0.48
    icture
    0.45
     Büyük
    0.44
     pakistan
    0.44
     akka
    0.44
     szeret
    0.43
     uppercase
    0.43
    salon
    0.42
     imageData
    0.42
    Activations Density 0.001%

    No Known Activations