© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12291
    Prev
    Next
    INDEX
    Explanations

    bomb, bleed, war, assassination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⁡</
    2.11
    mygray
    2.10
    <unused773>
    2.06
     कॉनकॉर्ड
    2.03
    [multimodal]
    2.03
    globalMap
    1.99
    reactant
    1.98
     mergeddata
    1.97
    =","><
    1.97
    <unused868>
    1.96
    POSITIVE LOGITS
    :
    1.47
     T
    1.44
     St
    1.29
     K
    1.27
     kan
    1.27
     W
    1.26
    ants
    1.24
     S
    1.23
     Masters
    1.20
    ant
    1.19
    Activations Density 0.159%

    No Known Activations