© 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. 29470
    Prev
    Next
    INDEX
    Explanations

    and Middle

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

    AI and physical states

    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
     Labrenzia
    0.54
     adatto
    0.54
    <unused2103>
    0.53
    ພວກເຮົາ
    0.53
     സെ
    0.52
     నేను
    0.51
     שהוא
    0.51
     அவரது
    0.50
     PON
    0.50
     Ekim
    0.48
    POSITIVE LOGITS
    んに
    0.44
    មី
    0.43
    ну
    0.43
     acids
    0.42
    تم
    0.42
    ំ
    0.41
    増
    0.41
     showcase
    0.40
    end
    0.40
     interf
    0.39
    Activations Density 0.000%

    No Known Activations