© 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-65K
    7. 7284
    Prev
    Next
    INDEX
    Explanations

    file path and variable names

    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_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
    6
    0.44
     x
    0.43
     Rb
    0.43
     femur
    0.43
     RBC
    0.43
     RBIs
    0.41
     kg
    0.41
     pentru
    0.41
     depositing
    0.41
    4
    0.40
    POSITIVE LOGITS
    如果有
    0.44
     શબ્
    0.44
     evocative
    0.42
    üedad
    0.42
    Unless
    0.42
     разум
    0.41
     suggestions
    0.41
    尝试
    0.41
    诚
    0.41
     স্বার্থ
    0.40
    Activations Density 0.365%

    No Known Activations