© 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. 29-GEMMASCOPE-2-RES-65K
    7. 3204
    Prev
    Next
    INDEX
    Explanations

    trickiest parts

    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_29_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
    <unused2118>
    0.64
     Goodwin
    0.51
     inexplic
    0.50
    ]")
    0.49
     excused
    0.49
    “)
    0.48
    螓
    0.48
    )"))
    0.47
    めて
    0.47
     pitiful
    0.47
    POSITIVE LOGITS
     http
    0.67
    ämm
    0.59
     Essay
    0.56
     https
    0.54
     www
    0.53
    ier
    0.53
     Apakah
    0.52
     процессе
    0.52
     آیا
    0.51
     contador
    0.51
    Activations Density 0.000%

    No Known Activations