© 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. 50557
    Prev
    Next
    INDEX
    Explanations

    foreign language texts

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

    commands or advice

    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
    šte
    0.48
    𝚕
    0.48
     cít
    0.47
     convain
    0.47
     directa
    0.45
     অভিনন্দন
    0.44
     っ
    0.44
     αυτο
    0.44
    लिसा
    0.44
    linearity
    0.44
    POSITIVE LOGITS
    ரா
    0.46
    子の
    0.44
    ולנד
    0.43
     Corpus
    0.43
    शंकर
    0.40
     Iter
    0.39
    ቆዳ
    0.39
    PROC
    0.38
    国の
    0.38
    Р
    0.38
    Activations Density 0.001%

    No Known Activations