© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 4736
    Prev
    Next
    INDEX
    Explanations

    date and time formats

    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
     ۔
    0.88
    east
    0.85
    Its
    0.81
     সুতরাং
    0.81
     입니다
    0.80
    salon
    0.80
    妘
    0.80
    θεση
    0.80
    hline
    0.80
     Unpublished
    0.80
    POSITIVE LOGITS
     you
    0.80
     Canadian
    0.67
     sagte
    0.66
     schrieb
    0.65
     '<
    0.65
     quis
    0.63
     বাধ
    0.61
    ጠቀ
    0.61
     my
    0.59
     myself
    0.58
    Activations Density 0.009%

    No Known Activations