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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8192
    Prev
    Next
    INDEX
    Explanations

    dynamic events and states

    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
     DSP
    0.91
    க்க
    0.88
    ર
    0.88
    ن
    0.87
     $[\
    0.87
    𝒚
    0.86
     ВО
    0.85
     $($
    0.85
     LSR
    0.84
     FT
    0.84
    POSITIVE LOGITS
    0
    1.10
     hề
    0.90
    Цена
    0.89
    Ш
    0.89
    Ş
    0.86
    1
    0.84
    То
    0.84
    2
    0.83
     besonders
    0.81
     graus
    0.81
    Activations Density 0.708%

    No Known Activations