© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2565
    Prev
    Next
    INDEX
    Explanations

    effect, room, clauses, registries, gender, solutions, model, affairs

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

    This neuron identifies formal, domain-specific jargon—particularly academic, regulatory, or technical nouns (e.g., “seminar,” “research,” “rules,” “commercial”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    。
    2.84
    ។
    2.61
    ։
    2.38
    ။
    2.34
    ।
    2.33
    ۔
    2.27
    }.
    2.22
    }$.
    2.14
    ®.
    2.13
    ™.
    2.08
    POSITIVE LOGITS
    ပါတယ်
    1.31
     (
    1.18
    ጣል
    1.17
    ራል
    1.13
     (!)
    1.09
     (“
    1.07
     ("
    1.02
     (‘
    0.99
    ራሉ
    0.93
    ዳል
    0.92
    Activations Density 0.561%

    No Known Activations