© 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. 35482
    Prev
    Next
    INDEX
    Explanations

    specific words and names

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

    technical explanations and code

    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
     ตาม
    0.52
     ieri
    0.51
     Fin
    0.51
     Gah
    0.51
     fin
    0.50
     ৃ
    0.49
     Apache
    0.48
     Marse
    0.48
     Nassau
    0.48
     (+
    0.47
    POSITIVE LOGITS
    ilege
    0.46
     వ్యవస్థ
    0.46
    ៥
    0.46
    reth
    0.44
    гле
    0.44
    ູ່
    0.44
    अर्थ
    0.42
    tida
    0.41
    intis
    0.41
    Larg
    0.41
    Activations Density 0.000%

    No Known Activations