© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 172738
    Prev
    Next
    INDEX
    Explanations

    kit, current, content, broken, basics, donate, doctors

    np_acts-logits-general · gemini-2.5-flash-lite

    methods require, means it will, engines to, stored it

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     ù
    0.42
     tentunya
    0.42
    ן
    0.42
    tbody
    0.42
     pastures
    0.41
    )?
    0.41
     cai
    0.41
     antibiotic
    0.40
     indications
    0.40
     electricity
    0.39
    POSITIVE LOGITS
     Unterkunft
    0.47
     analy
    0.46
    Produ
    0.46
     Einige
    0.46
    Decoding
    0.46
    𝟕
    0.46
     カスタ
    0.45
     Entwicklung
    0.44
     imani
    0.44
     Márquez
    0.44
    Activations Density 0.001%

    No Known Activations