© 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. 13-GEMMASCOPE-2-RES-65K
    7. 1646
    Prev
    Next
    INDEX
    Explanations

    on surfaces and locations

    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_65k_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
     consider
    1.47
    ア
    1.34
    를
    1.13
    e
    1.06
    RA
    1.03
     swear
    1.03
     dont
    1.01
     rest
    1.00
     imp
    1.00
    Re
    0.98
    POSITIVE LOGITS
     behalf
    3.07
     occasion
    1.63
    coproteins
    1.57
    slaught
    1.57
     základě
    1.54
     Grundlage
    1.48
    tabla
    1.47
    夰
    1.43
    etime
    1.43
     tatha
    1.41
    Activations Density 0.245%

    No Known Activations