© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 772
    Prev
    Next
    INDEX
    Explanations

    Punctuation and separators

    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_13_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
     *
    1.15
     tap
    1.14
     **
    1.10
     close
    1.09
     "*
    1.09
     same
    1.07
     pre
    1.05
     an
    1.03
     perform
    1.03
    elé
    1.03
    POSITIVE LOGITS
    _
    1.73
    #
    1.25
    %
    1.17
    -
    1.09
    With
    1.07
    And
    1.05
    We
    1.04
    Of
    1.01
    university
    1.01
    untuk
    1.01
    Activations Density 0.802%

    No Known Activations