© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2653
    Prev
    Next
    INDEX
    Explanations

    bullet points or numbered lists

    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_17_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
    áš
    0.71
    ＝
    0.70
     wei
    0.69
    ADESH
    0.67
    MJ
    0.67
     AN
    0.66
    ensão
    0.66
     digitally
    0.66
     verdadeira
    0.65
    మ్
    0.65
    POSITIVE LOGITS
    spam
    0.94
    occas
    0.89
     者
    0.87
    tort
    0.87
    in
    0.83
     utilizzati
    0.81
    hobby
    0.81
    animals
    0.80
    ሳይ
    0.80
     uter
    0.78
    Activations Density 0.471%

    No Known Activations