© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2249
    Prev
    Next
    INDEX
    Explanations

    2-

    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_22_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
    iro
    0.70
    keyup
    0.67
    *}$
    0.65
     ब्यूरो
    0.64
     relâche
    0.64
    یکٹر
    0.63
     highlights
    0.61
     Illustrator
    0.60
    topLeft
    0.60
     apasion
    0.60
    POSITIVE LOGITS
     Conventional
    0.70
     county
    0.63
    Vers
    0.61
     j
    0.61
    nons
    0.60
     Daff
    0.60
     enfrentar
    0.60
    犹豫
    0.59
     Ranc
    0.59
    વો
    0.59
    Activations Density 0.114%

    No Known Activations