© 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. 204056
    Prev
    Next
    INDEX
    Explanations

    bachelor or vocational

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

    broad overviews and analyses

    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
     производителя
    0.48
    dword
    0.47
     legume
    0.46
    꽝
    0.46
    ̏
    0.45
    довж
    0.45
     ناک
    0.44
     pessoais
    0.43
    ☘
    0.43
    czka
    0.43
    POSITIVE LOGITS
     viewer
    0.49
    ק
    0.47
     newsc
    0.45
    parks
    0.43
    est
    0.42
    学習
    0.42
     jsonObj
    0.42
     റെ
    0.42
     Ontology
    0.42
     ವ್ಯವ
    0.41
    Activations Density 0.000%

    No Known Activations