© 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. 3385
    Prev
    Next
    INDEX
    Explanations

    Collections, Drawing, IO

    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
    ್ಣ
    1.36
    йде
    1.34
    т
    1.30
     homomorphism
    1.29
    মি
    1.28
    тят
    1.27
    ен
    1.25
     longstanding
    1.25
     photoelectron
    1.24
    м
    1.24
    POSITIVE LOGITS
    re
    1.89
    id
    1.71
    al
    1.63
    na
    1.62
    Z
    1.58
    K
    1.57
    l
    1.56
    C
    1.52
    V
    1.52
    nosti
    1.51
    Activations Density 0.012%

    No Known Activations