© 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. 78868
    Prev
    Next
    INDEX
    Explanations

    simple, plain, all, left, romantic

    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
    л
    0.60
    z
    0.56
    ж
    0.50
     থাকবে
    0.49
    ఛ
    0.49
     ஆவார்
    0.47
    as
    0.47
    ii
    0.47
    ü
    0.46
     Lunch
    0.46
    POSITIVE LOGITS
    心
    0.51
     diffeomorphism
    0.50
     anthracene
    0.45
     algebraically
    0.45
    弦
    0.44
    不
    0.43
     ਸਿੰ
    0.42
    燈
    0.42
    اعد
    0.42
     الخط
    0.42
    Activations Density 0.000%

    No Known Activations