© 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. 126648
    Prev
    Next
    INDEX
    Explanations

    automotive manufacturers' information

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

    AI learning and direct database use

    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
    àm
    0.53
    に戻
    0.52
    を作
    0.51
    ári
    0.50
    sthe
    0.50
    }:=
    0.49
    larni
    0.49
     بنی
    0.48
     頭
    0.48
    ượu
    0.48
    POSITIVE LOGITS
    гора
    0.52
     rapports
    0.43
     resets
    0.42
     quedan
    0.42
    حال
    0.41
    MOT
    0.40
    ھی
    0.40
    데요
    0.40
     Kuy
    0.40
    ছে
    0.40
    Activations Density 0.001%

    No Known Activations