© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 132683
    Prev
    Next
    INDEX
    Explanations

    depending on conditional

    np_acts-logits-general · gemini-2.5-flash-lite

    the neuron detects salient content words (important informational nouns/verbs) in explanatory or descriptive sentences.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     ناف
    0.47
    ourcen
    0.43
    genome
    0.41
    改
    0.40
     پھی
    0.40
    ност
    0.40
     改
    0.39
    winfo
    0.39
    ServiceInterface
    0.39
    Informe
    0.38
    POSITIVE LOGITS
     mnie
    0.39
     rejoin
    0.39
     rage
    0.38
     salaried
    0.36
    +#+#+
    0.36
     end
    0.36
    ссор
    0.36
    ப்பாள
    0.36
     jubil
    0.36
     avoidable
    0.36
    Activations Density 0.000%

    No Known Activations