Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 3986
    Prev
    Next
    INDEX
    Explanations

    explanation or problem statements

    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_16k_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
     („
    0.93
     («
    0.91
     તેણી
    0.85
     т
    0.84
     편
    0.81
     본
    0.80
     المصري
    0.80
     hereof
    0.79
     (!)
    0.79
     (=
    0.79
    POSITIVE LOGITS
     betterment
    0.94
     chamar
    0.91
     curd
    0.90
     crore
    0.88
     Helpline
    0.87
     surety
    0.83
     થી
    0.83
     falt
    0.83
     give
    0.82
     Aro
    0.82
    Activations Density 0.049%

    No Known Activations