© 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. 8046
    Prev
    Next
    INDEX
    Explanations

    home and related 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_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
     جذب
    0.66
    াণ
    0.66
     सेक्शन
    0.65
    ouncil
    0.65
     журнал
    0.64
    ylene
    0.64
     przysz
    0.64
    炷
    0.64
    avra
    0.64
     vyst
    0.63
    POSITIVE LOGITS
     home
    4.00
    home
    3.44
     Home
    3.25
    Home
    3.22
     HOME
    2.93
     thuis
    2.90
    HOME
    2.89
     дома
    2.84
     homes
    2.83
     домаш
    2.75
    Activations Density 0.305%

    No Known Activations