© 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. 11917
    Prev
    Next
    INDEX
    Explanations

    Court Decisions

    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
    SI
    1.32
    Follow
    1.27
     payback
    1.19
     सोबत
    1.17
     Follow
    1.13
    sman
    1.10
    ل
    1.08
     following
    1.07
     awareness
    1.07
     Axi
    1.07
    POSITIVE LOGITS
    ιτε
    1.38
     vrsta
    1.30
    꼽
    1.27
     význam
    1.26
    ディング
    1.24
     pén
    1.20
     regelmäßig
    1.18
    znak
    1.17
    멩
    1.17
     hvert
    1.15
    Activations Density 0.000%

    No Known Activations