© 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. 202388
    Prev
    Next
    INDEX
    Explanations

    no, desire, show, described, facilities, changes, seem

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

    technical terms and codes

    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
     vasculaire
    0.59
     للا
    0.51
    噹
    0.48
     جان
    0.48
     effusion
    0.48
     सीता
    0.47
     своими
    0.47
     আগমন
    0.46
     والاست
    0.46
     اللا
    0.46
    POSITIVE LOGITS
    G
    0.50
    CultureInfo
    0.50
    Job
    0.48
    K
    0.48
    t
    0.48
     FC
    0.47
    d
    0.47
    N
    0.47
    V
    0.47
    逑
    0.46
    Activations Density 0.001%

    No Known Activations