© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3196
    Prev
    Next
    INDEX
    Explanations

    Python code keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_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
     Let
    0.80
     върху
    0.80
     let
    0.78
     उसके
    0.77
     Letting
    0.75
    恁
    0.75
     Its
    0.74
    িনে
    0.74
     Straw
    0.74
     Str
    0.74
    POSITIVE LOGITS
    #
    0.70
    前期
    0.67
    """
    0.63
     potentials
    0.63
    atosis
    0.61
    ##
    0.61
    .#
    0.60
    rocytes
    0.60
     краски
    0.59
     décrite
    0.57
    Activations Density 0.178%

    No Known Activations