© 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. 28528
    Prev
    Next
    INDEX
    Explanations

    golf classic

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

    technical terms and 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
     বিদেশী
    0.50
     detr
    0.46
    原有
    0.46
    兼容
    0.45
    件事
    0.43
    经
    0.43
     eser
    0.42
    返回
    0.42
    一旦
    0.42
     可能
    0.42
    POSITIVE LOGITS
     Patrol
    0.49
    🏖
    0.47
     spines
    0.47
    oms
    0.46
    نیم
    0.46
    🐬
    0.46
     lifegu
    0.45
    ™,
    0.45
     Ultra
    0.44
     sommer
    0.44
    Activations Density 0.000%

    No Known Activations