© 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. 79787
    Prev
    Next
    INDEX
    Explanations

    Testament often, and the, that have

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

    state, limited, available

    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
     telephones
    0.58
     partisan
    0.50
     partisans
    0.45
     ambulances
    0.45
     Canadians
    0.44
     phones
    0.44
     PCs
    0.44
    鹬
    0.44
    طم
    0.43
     hoses
    0.43
    POSITIVE LOGITS
    castle
    0.49
     inhibit
    0.47
     বাঁচাতে
    0.47
    góc
    0.46
     texture
    0.45
     પ્રતિબિં
    0.45
     prawidł
    0.45
     cryst
    0.45
     metabolismo
    0.45
     ગો
    0.44
    Activations Density 0.000%

    No Known Activations