© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4716
    Prev
    Next
    INDEX
    Explanations

    not comfortable sharing

    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
    <unused624>
    1.13
    <unused419>
    1.11
    <unused228>
    1.11
     baseApiPath
    1.11
     Pusenkoff
    1.09
    <unused2058>
    1.09
    <unused282>
    1.08
    <unused268>
    1.07
    <unused308>
    1.06
    竰
    1.06
    POSITIVE LOGITS
    ing
    0.92
      
    0.71
     Cond
    0.69
    mean
    0.65
     User
    0.63
     user
    0.62
     mean
    0.60
    user
    0.59
     D
    0.59
    ial
    0.57
    Activations Density 0.046%

    No Known Activations