© 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. 20762
    Prev
    Next
    INDEX
    Explanations

    careers page, pricing can subscribe, graphic biography, sum renting

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

    even if

    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
    远离
    0.50
    ϊ
    0.49
    üler
    0.47
    ų
    0.44
    
    0.42
    jä
    0.42
     Scul
    0.42
    NonUser
    0.42
    ä
    0.42
    μορφ
    0.42
    POSITIVE LOGITS
     bacilli
    0.54
     liters
    0.54
    ቝ
    0.51
     antagonism
    0.50
    GUNDABAD
    0.49
     extractive
    0.49
     hypotheses
    0.46
     hostilities
    0.46
     anarchy
    0.46
     hypothesize
    0.46
    Activations Density 0.000%

    No Known Activations