© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14270
    Prev
    Next
    INDEX
    Explanations

    darker coloring, textures, website affiliation

    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
    טים
    1.23
    cribable
    1.19
    cripts
    1.18
    ீ
    1.15
    Tatar
    1.14
    ൂപ
    1.12
    दात
    1.10
    हल
    1.09
     superficially
    1.09
    γραφ
    1.08
    POSITIVE LOGITS
     Any
    1.28
    굿
    1.17
    Any
    1.16
    에게
    1.14
    が良い
    1.12
     happy
    1.11
    ukt
    1.10
    わない
    1.09
     Lage
    1.08
     خلاف
    1.07
    Activations Density 0.000%

    No Known Activations