© 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. 12923
    Prev
    Next
    INDEX
    Explanations

    freeCodeCamp and Google services

    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
     tested
    1.30
    ة
    1.25
    e
    1.24
    वन
    1.23
    ed
    1.21
    as
    1.18
     plain
    1.16
     by
    1.15
    i
    1.09
     المص
    1.09
    POSITIVE LOGITS
     companionship
    2.37
     prostitutes
    2.35
     conversaciones
    2.30
     autoestima
    2.28
     comerciantes
    2.27
     prostitution
    2.23
     Geografia
    2.23
     confeder
    2.21
     taiwan
    2.18
     mujeres
    2.18
    Activations Density 0.194%

    No Known Activations