© 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. 61399
    Prev
    Next
    INDEX
    Explanations

    author's actions or descriptions

    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
    <unused743>
    0.42
    BlockFit
    0.37
    <unused716>
    0.37
    <unused251>
    0.36
    <unused289>
    0.36
     RetValue
    0.35
     imputation
    0.35
     thisStudent
    0.35
     subcluster
    0.35
    磋
    0.35
    POSITIVE LOGITS
    0.38
    Y
    0.38
    he
    0.37
     $
    0.35
    B
    0.34
    ab
    0.34
    ar
    0.34
    ig
    0.33
    ir
    0.33
    at
    0.32
    Activations Density 0.067%

    No Known Activations