© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6697
    Prev
    Next
    INDEX
    Explanations

    a specific value or statement

    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_24_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
    Οι
    0.66
     volontà
    0.66
    𝓶
    0.61
    ⁇
    0.60
     Sự
    0.58
    दर
    0.57
    adaş
    0.57
     tarses
    0.57
    ጅ
    0.57
    态
    0.57
    POSITIVE LOGITS
     yaitu
    0.75
     sebagai
    0.66
     sebagaimana
    0.66
     adalah
    0.62
     Called
    0.61
     suffers
    0.61
     yakni
    0.60
     Supplemental
    0.59
     affliction
    0.59
     Perhaps
    0.59
    Activations Density 0.000%

    No Known Activations