© 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. 40-GEMMASCOPE-2-RES-65K
    7. 3078
    Prev
    Next
    INDEX
    Explanations

    tabular, alignment, and tikz formatting

    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_40_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
    setOutput
    0.52
    لود
    0.44
    randomIndex
    0.43
    ഹം
    0.40
     মূর্তি
    0.40
    バイク
    0.40
    addUser
    0.39
    昧
    0.39
    bytecode
    0.39
    jour
    0.39
    POSITIVE LOGITS
     alignment
    1.17
     Alignment
    1.09
     aligned
    1.03
     align
    1.02
     Align
    1.00
     aligning
    0.95
    Align
    0.90
    alignment
    0.90
     alignments
    0.89
    Alignment
    0.88
    Activations Density 0.055%

    No Known Activations