© 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. 3208
    Prev
    Next
    INDEX
    Explanations

    electrical and electricity concepts

    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
    giraffe
    0.76
     caches
    0.75
    ヅ
    0.67
     Sapir
    0.66
     Ubuntu
    0.65
     Merlot
    0.64
    ohama
    0.64
    樽
    0.63
    Canonical
    0.63
    steiner
    0.63
    POSITIVE LOGITS
     electrical
    4.52
     electric
    4.41
     elec
    4.24
    Electrical
    4.20
     Electrical
    4.16
     Electric
    4.12
    Electric
    4.05
     elektr
    4.04
     электро
    4.04
    electrical
    4.00
    Activations Density 0.348%

    No Known Activations