© 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. 51084
    Prev
    Next
    INDEX
    Explanations

    kontrast Australie downloads tekst

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

    key performance, system, JSON, directly

    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
    על
    0.52
     ጠ
    0.48
    𝑻
    0.48
     เด็ก
    0.47
    ]@
    0.47
     benefactor
    0.46
    𝑬
    0.46
     Squirrel
    0.45
     كام
    0.45
    সন্ধ
    0.45
    POSITIVE LOGITS
    arsk
    0.48
     mets
    0.47
     tekst
    0.46
    downloads
    0.46
    2
    0.46
    novo
    0.46
    emers
    0.46
     kapital
    0.46
     kontrast
    0.45
     Australie
    0.45
    Activations Density 0.000%

    No Known Activations