© 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. 117614
    Prev
    Next
    INDEX
    Explanations

    language diverse input

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

    git clone ssh

    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
     Add
    0.49
    _
    0.46
    ,@
    0.44
    b
    0.44
     Patio
    0.44
    Add
    0.44
    Intro
    0.42
     monet
    0.42
     Saigon
    0.42
     add
    0.42
    POSITIVE LOGITS
     modelli
    0.50
    穩
    0.50
     বন্ধুত্ব
    0.49
    醫院
    0.48
    נס
    0.48
    ಪಾ
    0.46
    ಪೆ
    0.46
    𝘺
    0.46
     braced
    0.46
    䧺
    0.46
    Activations Density 0.001%

    No Known Activations