© 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. 149410
    Prev
    Next
    INDEX
    Explanations

    CSA purchase, Office questions, ADA

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

    legal, political, or technical descriptions

    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
    শী
    0.46
    projectName
    0.44
    ರೀಕ್ಷ
    0.44
     giỏi
    0.44
    ଥି
    0.44
    立方
    0.43
    运用
    0.43
    饬
    0.43
    蹦
    0.42
    capac
    0.40
    POSITIVE LOGITS
    아
    0.59
     гражда
    0.54
    นัก
    0.54
     prized
    0.53
    セ
    0.52
    의
    0.51
     political
    0.51
    i
    0.50
     politically
    0.49
     gambler
    0.47
    Activations Density 0.000%

    No Known Activations