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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 8397
    Prev
    Next
    INDEX
    Explanations

    section breaks or headers

    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
    ς
    1.74
     anteriores
    1.67
     edizione
    1.51
    கள்
    1.50
    _{-}$
    1.45
    THING
    1.44
    𝐬
    1.41
     semn
    1.38
     anderer
    1.35
    ానికి
    1.34
    POSITIVE LOGITS
    ان
    2.48
    an
    2.38
    на
    2.34
    is
    1.99
    in
    1.80
    न
    1.76
    on
    1.71
    কে
    1.70
    ת
    1.70
    ಾ
    1.70
    Activations Density 0.510%

    No Known Activations