© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 6568
    Prev
    Next
    INDEX
    Explanations

    following instructions, safety, offers

    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
    нь
    0.69
    на
    0.68
     мо
    0.66
     accom
    0.66
    zee
    0.66
    മാക
    0.66
     accommodation
    0.66
     о
    0.66
    れい
    0.66
     κο
    0.65
    POSITIVE LOGITS
    椽
    0.87
    듀
    0.77
     infuri
    0.76
     تلوار
    0.75
     Dois
    0.74
     capazes
    0.73
    ك
    0.73
     insectes
    0.72
    tri
    0.71
     terrifying
    0.71
    Activations Density 0.001%

    No Known Activations