© 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. 10827
    Prev
    Next
    INDEX
    Explanations

    Comments in structured text

    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
     Ferien
    1.50
    덱
    1.47
    Refreshing
    1.47
    搐
    1.46
     COSTS
    1.45
     Góc
    1.45
     PEACE
    1.43
    㑔
    1.43
     hátsó
    1.42
     Proced
    1.41
    POSITIVE LOGITS
    ’
    1.25
    :
    1.19
     was
    1.15
     is
    1.15
     initially
    1.14
     ber
    1.12
     originally
    1.10
     actually
    1.09
    ʻ
    1.09
    tol
    1.08
    Activations Density 0.182%

    No Known Activations