© 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
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-262K
    4. 4474
    Prev
    Next
    INDEX
    Explanations

    categories or aspects of something

    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_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
     Classical
    0.37
    :
    0.36
    )
    0.36
     European
    0.35
     Qué
    0.34
     Eddy
    0.34
     (=
    0.34
     OL
    0.33
    GA
    0.33
     tarsi
    0.33
    POSITIVE LOGITS
    arcie
    0.42
     aswell
    0.40
    radius
    0.40
     konusunda
    0.38
    يدك
    0.37
     парамет
    0.37
     prowess
    0.37
    த்தையும்
    0.37
    realm
    0.37
    abilitas
    0.37
    Activations Density 0.149%

    No Known Activations