© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2162
    Prev
    Next
    INDEX
    Explanations

    user question

    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_16_width_65k_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
    ↵↵
    0.45
    ת
    0.35
     partnerships
    0.34
    ↵
    0.33
    תה
    0.33
    ↵↵↵
    0.32
     group
    0.31
     progr
    0.31
    6
    0.31
    ל
    0.30
    POSITIVE LOGITS
    UD
    0.36
    IN
    0.35
    <unused1008>
    0.32
    avacanam
    0.31
    ON
    0.31
    ANT
    0.31
    IG
    0.30
    OM
    0.29
    UP
    0.29
    𝘺
    0.29
    Activations Density 0.001%

    No Known Activations