© 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. 1120
    Prev
    Next
    INDEX
    Explanations

    technical terms or systems

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

    Attention, augmented, certified, SSD, CSS, Database

    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
    abbanti
    0.41
    诤
    0.40
    锼
    0.38
    绦
    0.38
    疖
    0.36
     appunto
    0.35
     সুস্পষ্ট
    0.34
     recense
    0.34
     एनिमल्स
    0.34
     nämlich
    0.34
    POSITIVE LOGITS
    -
    0.51
    等の
    0.49
    ר
    0.46
    型
    0.45
    などの
    0.44
    9
    0.41
    等多
    0.40
    achtige
    0.39
     등의
    0.39
    type
    0.38
    Activations Density 0.226%

    No Known Activations