© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11828
    Prev
    Next
    INDEX
    Explanations

    bitwise operations

    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
    Θ
    2.68
    יא
    2.65
    s
    2.61
    subject
    2.50
    銇
    2.43
    ACP
    2.37
    躁
    2.34
    ađ
    2.33
    sset
    2.30
    crt
    2.30
    POSITIVE LOGITS
    തും
    2.21
     Fhir
    2.15
     subsequence
    2.03
     manj
    1.98
    atiques
    1.98
    boten
    1.95
    躇
    1.93
    agers
    1.92
    osť
    1.91
    igue
    1.91
    Activations Density 0.014%

    No Known Activations