© 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. 104178
    Prev
    Next
    INDEX
    Explanations

    seeking, looking for

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

    ai\_text\_completion function calls

    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
    ্লীল
    0.52
     ANTON
    0.50
     betrieb
    0.48
     lipids
    0.46
    जनन
    0.45
     bullied
    0.44
     guar
    0.44
    🌮
    0.44
     consented
    0.44
    西
    0.43
    POSITIVE LOGITS
    tract
    0.54
    racing
    0.53
    insect
    0.53
    raz
    0.52
     மிகப்பெ
    0.51
    ub
    0.51
    alak
    0.50
    isateur
    0.50
    recall
    0.50
    great
    0.49
    Activations Density 0.000%

    No Known Activations