© 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-262K
    7. 195919
    Prev
    Next
    INDEX
    Explanations

    policies and potential

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

    `cliff means` or `hash of`

    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_262k_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
    吣
    0.49
     ձ
    0.47
    跹
    0.46
    蛳
    0.45
    美国的
    0.45
     kív
    0.43
    还
    0.43
    旲
    0.43
    离开
    0.42
    dDevice
    0.42
    POSITIVE LOGITS
     deterred
    0.48
     negotiable
    0.47
     generational
    0.46
     deterior
    0.46
    only
    0.45
     parole
    0.45
     cumple
    0.45
     punctuation
    0.44
     malleable
    0.44
    ONLY
    0.44
    Activations Density 0.000%

    No Known Activations