© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8100
    Prev
    Next
    INDEX
    Explanations

    stereoscopic vision and energy destabilization

    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_13_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
    ’
    1.39
    ële
    1.34
     растений
    1.32
     растения
    1.30
    ísim
    1.26
    '
    1.24
    spath
    1.24
    ë
    1.23
    フオク
    1.20
    щими
    1.20
    POSITIVE LOGITS
    urge
    1.75
    radar
    1.50
    LIM
    1.46
     महज
    1.46
    ρων
    1.44
    无
    1.40
    reported
    1.39
    łon
    1.39
    टेज
    1.38
    মুনা
    1.38
    Activations Density 0.000%

    No Known Activations