Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 44583
    Prev
    Next
    INDEX
    Explanations

    dictionary mapping labels to values

    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
     ее
    1.04
     or
    0.97
     وهذه
    0.84
     её
    0.84
    她的
    0.81
     and
    0.80
     이를
    0.80
     --
    0.79
     її
    0.78
     និង
    0.77
    POSITIVE LOGITS
     subtypes
    1.16
    でない
    1.16
    ategori
    1.13
     verwendeten
    1.11
     Codes
    1.10
     evitare
    1.09
     categoria
    1.08
     kawaida
    1.08
     desactiv
    1.07
     falsch
    1.05
    Activations Density 0.362%

    No Known Activations