© 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. 14434
    Prev
    Next
    INDEX
    Explanations

    inclusive communication, conflict detection, repeats

    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
    Какие
    1.53
    дол
    1.51
    Iz
    1.40
    大多数
    1.39
    很少
    1.37
    аль
    1.36
    ปลี่ยน
    1.36
    ɑ
    1.35
    нодоро
    1.34
    ilihan
    1.33
    POSITIVE LOGITS
     detached
    1.44
     tunnels
    1.43
     insight
    1.42
     packed
    1.35
     fantastic
    1.34
     extracted
    1.34
     divine
    1.33
     idea
    1.31
     chamber
    1.31
     turbines
    1.31
    Activations Density 0.000%

    No Known Activations