© 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. 30350
    Prev
    Next
    INDEX
    Explanations

    numbers and booleans

    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
    ل
    3.80
    ו
    3.19
    in
    3.16
    ри
    3.02
    на
    2.97
    و
    2.80
    jenigen
    2.67
    ת
    2.63
    ed
    2.53
    てください
    2.52
    POSITIVE LOGITS
    ে
    2.80
    ి
    2.73
    ্লাহ
    2.44
    కు
    2.31
    써
    2.28
    i
    2.27
    ი
    2.22
    ductory
    2.17
     efectu
    2.14
    ه
    2.08
    Activations Density 0.040%

    No Known Activations