© 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. 69934
    Prev
    Next
    INDEX
    Explanations

    use a or the

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

    Golang microservice development

    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
     pensions
    0.52
    ﾛ
    0.50
    KOV
    0.49
     halls
    0.48
    た
    0.48
     約
    0.48
    約
    0.46
    楽器
    0.46
    దాయ
    0.45
     pension
    0.45
    POSITIVE LOGITS
    ieszcz
    0.49
     karşınız
    0.48
    akiem
    0.48
    ניים
    0.48
    ᾶ
    0.47
    "=
    0.47
     gördüğünüz
    0.46
    ami
    0.45
     Trie
    0.45
     Disaster
    0.45
    Activations Density 0.001%

    No Known Activations