© 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. 11837
    Prev
    Next
    INDEX
    Explanations

    one was

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

    code functions with types

    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
    Б
    0.56
    Ἄ
    0.55
    ോട്ട്
    0.53
    И
    0.53
    ਾ
    0.52
     Бого
    0.51
    ა
    0.50
    р
    0.50
    С
    0.50
    戽
    0.49
    POSITIVE LOGITS
    heba
    0.46
    ravy
    0.45
     balcon
    0.44
    CPC
    0.43
     mottled
    0.43
     शुक्ल
    0.42
    hav
    0.42
     tingkat
    0.42
     buddhav
    0.42
     विध
    0.41
    Activations Density 0.000%

    No Known Activations