© 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-262K
    7. 136675
    Prev
    Next
    INDEX
    Explanations

    assigning and unpacking multiple values

    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_262k_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
     lift
    0.39
    alir
    0.38
     ശബരിമല
    0.38
     flusso
    0.37
     LIST
    0.35
    ″]
    0.35
    ListName
    0.35
     Brune
    0.35
     Lift
    0.35
    ဵ
    0.35
    POSITIVE LOGITS
    Avoiding
    0.48
    getValue
    0.45
     unpacking
    0.44
    igning
    0.42
    Parsing
    0.42
     unpacked
    0.41
    优雅
    0.41
     صحیح
    0.41
     సాం
    0.40
     elegantly
    0.39
    Activations Density 0.017%

    No Known Activations