© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8509
    Prev
    Next
    INDEX
    Explanations

    web urls with script extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⅰ
    0.79
    ៧
    0.75
     இ
    0.72
    Tri
    0.72
     знаходиться
    0.72
    titulo
    0.71
    avano
    0.71
    Pine
    0.71
    tri
    0.71
    Ə
    0.71
    POSITIVE LOGITS
     rack
    0.77
     implement
    0.75
     לפ
    0.74
     catch
    0.73
     belast
    0.73
    ?
    0.71
     scattering
    0.70
     dictate
    0.70
    তীশ
    0.70
     fentanyl
    0.70
    Activations Density 0.007%

    No Known Activations