© 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
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8363
    Prev
    Next
    INDEX
    Explanations

    when, where, what

    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
     \%$
    0.55
    okhlov
    0.52
    는
    0.49
    aarr
    0.46
     ಮಾಡಲು
    0.46
     بما
    0.45
    ஞ்ஞான
    0.45
    တော့
    0.45
     যদি
    0.44
     كما
    0.44
    POSITIVE LOGITS
    ઉસ
    0.48
    檛
    0.45
    tional
    0.43
     illustrious
    0.43
     Lieut
    0.42
    deen
    0.41
     statesmen
    0.40
    нің
    0.40
    postcss
    0.40
     rota
    0.40
    Activations Density 0.559%

    No Known Activations