© 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. 196102
    Prev
    Next
    INDEX
    Explanations

    language, coffee, online, story

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

    savings and fuel costs

    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
     Şu
    0.56
    Ş
    0.55
    𝔸
    0.53
     amacıyla
    0.51
    现有
    0.50
     hoera
    0.48
    rvGroup
    0.47
     şu
    0.47
     مصنوعی
    0.47
    Nv
    0.47
    POSITIVE LOGITS
    рони
    0.47
    lk
    0.46
     РО
    0.46
    он
    0.45
     NTFS
    0.45
    ал
    0.44
    чку
    0.43
    ↵
    0.43
     Variants
    0.43
     indicative
    0.43
    Activations Density 0.000%

    No Known Activations