© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10407
    Prev
    Next
    INDEX
    Explanations

    need to

    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_9_width_262k_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
    epsilon
    0.77
    𝐞
    0.73
    tail
    0.64
    Number
    0.64
     axios
    0.64
    david
    0.64
    Remainder
    0.63
    Suppose
    0.63
    어
    0.62
    avait
    0.62
    POSITIVE LOGITS
     rebut
    0.70
     hundred
    0.69
     vet
    0.69
     چنان
    0.68
    ካከል
    0.68
     অনুগ্রহ
    0.67
    үр
    0.64
     muh
    0.62
     sne
    0.62
     idee
    0.62
    Activations Density 0.036%

    No Known Activations