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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 921
    Prev
    Next
    INDEX
    Explanations

    invasion, war, conflict

    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
     aina
    0.62
    end
    0.61
    ch
    0.60
     always
    0.58
    bi
    0.56
    age
    0.56
    eb
    0.55
    j
    0.55
    છ
    0.55
    be
    0.54
    POSITIVE LOGITS
     shocking
    1.17
     insults
    1.14
     threatening
    1.12
    嗆
    1.10
     enraged
    1.10
     সিগারে
    1.08
     insulting
    1.08
     unleashing
    1.07
     공격
    1.06
     catalysis
    1.06
    Activations Density 0.225%

    No Known Activations