© 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-16K
    7. 5679
    Prev
    Next
    INDEX
    Explanations

    generalizations versus specifics

    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_16k_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
     dekh
    0.52
    𝔀
    0.51
    綃
    0.50
     vaccinate
    0.49
     kerosene
    0.48
    𓐄
    0.47
     nmea
    0.47
     thermocouple
    0.46
     saath
    0.46
    ホル
    0.46
    POSITIVE LOGITS
    '
    0.66
     '
    0.54
    尔
    0.53
    ick
    0.51
     Code
    0.48
    \
    0.48
    yl
    0.48
    st
    0.46
    ent
    0.46
    il
    0.46
    Activations Density 0.001%

    No Known Activations