© 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. 2636
    Prev
    Next
    INDEX
    Explanations

    /us/therapists URLs

    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
     बढ
    0.76
    圭
    0.66
    гез
    0.66
     Séance
    0.64
    緹
    0.64
    plik
    0.63
    rale
    0.63
    gespr
    0.62
    쿠
    0.62
    schirm
    0.61
    POSITIVE LOGITS
     PDP
    0.80
     APC
    0.79
     NGF
    0.73
    PDP
    0.72
    慣
    0.71
     Academic
    0.71
    EB
    0.68
     searchObject
    0.68
    VM
    0.67
    ∈</
    0.66
    Activations Density 0.033%

    No Known Activations