© 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. 1963
    Prev
    Next
    INDEX
    Explanations

    broad capabilities, accessibility, appeal, assessment

    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
    り
    2.58
    ிறது
    2.41
    вая
    2.30
    い
    2.28
    いた
    2.27
    ção
    2.19
    서
    2.19
    ция
    2.17
    сть
    2.16
    ться
    2.11
    POSITIVE LOGITS
    kennung
    2.00
    이니까
    1.95
     nämlich
    1.88
    ता
    1.85
    k
    1.81
     durs
    1.78
    heur
    1.73
    unnumbered
    1.73
    \"
    1.70
    Emojis
    1.70
    Activations Density 0.049%

    No Known Activations