© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8581
    Prev
    Next
    INDEX
    Explanations

    example story properly description time

    np_acts-logits-general · gemini-2.5-flash-lite

    listing concepts and definitions

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptive explanatory text

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     avion
    0.49
    ↵
    0.46
     Ron
    0.42
     Kirk
    0.42
     Ava
    0.42
     @
    0.41
     Zach
    0.41
     Westport
    0.41
     Rae
    0.40
     Rogers
    0.40
    POSITIVE LOGITS
    Expiry
    0.44
     말미암
    0.44
     그다
    0.43
     ascertaining
    0.42
    很是
    0.41
    <0xD6>
    0.41
    ictionnaire
    0.40
    :...
    0.40
    ʼn
    0.40
     まあ
    0.40
    Activations Density 0.678%

    No Known Activations