© 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. 76829
    Prev
    Next
    INDEX
    Explanations

    assign id

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

    topic introduction or state change

    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
    ان
    0.57
    fills
    0.50
     मोठी
    0.47
    苃
    0.46
    敔
    0.46
    lycer
    0.45
    amending
    0.45
    श्याम
    0.45
    barth
    0.45
     उपलब्ध
    0.45
    POSITIVE LOGITS
     problematic
    0.49
    พลิ
    0.48
    кция
    0.47
    :'',
    0.46
     শব্দটি
    0.46
     octombrie
    0.46
    ='',
    0.44
     dė
    0.44
    ا۔
    0.44
    টিল
    0.43
    Activations Density 0.000%

    No Known Activations