© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12416
    Prev
    Next
    INDEX
    Explanations

    sacrifice and death

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

    story requests and specific scenarios

    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_31_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
    ญ
    0.55
    ioid
    0.52
    форд
    0.50
     जखमी
    0.50
    idać
    0.50
    韬
    0.50
    强势
    0.49
    噤
    0.49
    Hora
    0.49
    肠
    0.49
    POSITIVE LOGITS
     life
    0.52
     preparatory
    0.50
     cheerfully
    0.50
     Arithmetic
    0.48
     playroom
    0.46
     Northwestern
    0.45
     arithmetic
    0.45
     Northwest
    0.44
     unlimited
    0.44
     cheerful
    0.44
    Activations Density 0.004%

    No Known Activations