© 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. 76728
    Prev
    Next
    INDEX
    Explanations

    world car

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

    code, lists, variables

    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
     pokaz
    0.45
     në
    0.44
     เฉ
    0.44
     bądź
    0.44
    铨
    0.44
     ২০২৩
    0.44
     CUDA
    0.43
     দুর্ঘটনার
    0.43
     göst
    0.42
     และ
    0.42
    POSITIVE LOGITS
    accent
    0.49
    as
    0.47
     depressed
    0.47
    కు
    0.44
    小
    0.44
    ্যাথ
    0.44
     unwillingness
    0.44
    家
    0.43
    ម្ល
    0.43
    ass
    0.42
    Activations Density 0.000%

    No Known Activations