© 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. 44034
    Prev
    Next
    INDEX
    Explanations

    negative outcomes or costs

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

    technical jargon and abbreviations

    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
     supporters
    0.46
     précédentes
    0.45
     今回
    0.45
     Supporters
    0.44
    ऽ
    0.44
     interests
    0.42
    comm
    0.42
    事的
    0.41
    Selectors
    0.40
     شر
    0.39
    POSITIVE LOGITS
     మూడు
    0.46
    ழ்ப
    0.46
     చిత్రం
    0.46
    甾
    0.44
     beş
    0.44
     пять
    0.43
     boosted
    0.43
    季节
    0.43
    廰
    0.43
    工房
    0.42
    Activations Density 0.000%

    No Known Activations