© 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. 25039
    Prev
    Next
    INDEX
    Explanations

    abstract methods, ABC analysis, only one

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

    python abc module

    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
    你想
    0.48
    你能
    0.46
     amelyet
    0.46
     upgraded
    0.44
    美女
    0.43
    ))
    0.42
     पहनी
    0.42
    能
    0.42
    美元
    0.41
    你有
    0.41
    POSITIVE LOGITS
    AYS
    0.45
    defence
    0.45
    arek
    0.43
    ITA
    0.43
     שני
    0.42
     fantastical
    0.41
     Ums
    0.40
     появляются
    0.40
     maestros
    0.40
    専門
    0.40
    Activations Density 0.000%

    No Known Activations