© 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. 2836
    Prev
    Next
    INDEX
    Explanations

    roll scaling

    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
    I
    0.69
    )
    0.65
    Б
    0.63
    З
    0.63
    Т
    0.61
    )'
    0.60
    }'
    0.60
     copyspace
    0.59
    -
    0.59
    י
    0.59
    POSITIVE LOGITS
     Finance
    0.57
     জম
    0.57
    PatientR
    0.55
     それ
    0.55
    轪
    0.53
     車
    0.52
     అంతే
    0.52
    ed
    0.52
     武田
    0.51
    icator
    0.51
    Activations Density 0.000%

    No Known Activations