© 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. 9145
    Prev
    Next
    INDEX
    Explanations

    ideas and ideation

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

    ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     question
    0.42
    andfeel
    0.41
     bowl
    0.39
    irical
    0.39
     عادت
    0.38
    etik
    0.38
    स्थापन
    0.38
    </strong>
    0.38
     मणिपुर
    0.38
    制造商
    0.37
    POSITIVE LOGITS
     IDE
    0.72
     idées
    0.68
     ideas
    0.64
     Ide
    0.63
    Ide
    0.63
    IDE
    0.63
     Ideas
    0.63
     ide
    0.61
     идеи
    0.61
    Ideas
    0.60
    Activations Density 0.080%

    No Known Activations