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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 3973
    Prev
    Next
    INDEX
    Explanations

    securities and services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ة
    1.35
    ین
    1.33
    ية
    1.26
    یط
    1.24
    та
    1.20
    く
    1.20
    ير
    1.19
    ہ
    1.19
    Chars
    1.18
    På
    1.16
    POSITIVE LOGITS
    ä
    1.25
     Bagi
    1.23
     neler
    1.20
     rady
    1.18
     dirigeants
    1.18
    ⮚
    1.16
     rosemary
    1.15
     regelmatig
    1.15
     powert
    1.14
     koje
    1.13
    Activations Density 0.045%

    No Known Activations