© 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. 50501
    Prev
    Next
    INDEX
    Explanations

    conjunctions or alternatives

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

    letters and their purpose

    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
    AssignableFrom
    0.50
    ጺ
    0.50
    状態
    0.49
    𠃌
    0.49
    iccation
    0.49
     सफाया
    0.48
    xAxis
    0.48
    ே
    0.47
    thisComponent
    0.47
    銛
    0.47
    POSITIVE LOGITS
     või
    0.55
    的事情
    0.48
     veya
    0.48
     alebo
    0.46
    0.45
     atau
    0.43
     maupun
    0.42
     किंवा
    0.42
     believe
    0.41
     oder
    0.41
    Activations Density 0.000%

    No Known Activations