© 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. 26534
    Prev
    Next
    INDEX
    Explanations

    company names and abbreviations

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

    initialy comments catches it to panel

    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
    線を
    0.46
    ალ
    0.46
    Также
    0.44
    り
    0.43
    зировать
    0.43
    金を
    0.42
     lubricants
    0.42
    ising
    0.41
     subalgebras
    0.41
    ولی
    0.41
    POSITIVE LOGITS
     CBP
    0.55
     OPPO
    0.49
     ŝ
    0.48
    ANS
    0.47
    बंधनाच्या
    0.46
     AEC
    0.46
     Cre
    0.45
     CEC
    0.45
    INO
    0.45
     Mobile
    0.44
    Activations Density 0.000%

    No Known Activations