© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 123949
    Prev
    Next
    INDEX
    Explanations

    toggle button

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     язык
    0.48
    <0xAD>
    0.48
    )、
    0.48
    tl
    0.44
     литератур
    0.43
    を用いて
    0.43
    aras
    0.42
    using
    0.42
     następnie
    0.42
    use
    0.41
    POSITIVE LOGITS
    ات
    0.55
     제가
    0.47
    ድ
    0.46
     ರಾಜ್ಯ
    0.46
    گون
    0.44
     impunity
    0.44
     endanger
    0.43
     держави
    0.43
    ం
    0.43
     shortfall
    0.42
    Activations Density 0.003%

    No Known Activations