© 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. 136067
    Prev
    Next
    INDEX
    Explanations

    foreign language words and characters

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

    web links and technical terms

    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
     حساب
    0.48
     سور
    0.48
    ansen
    0.46
    ᑖ
    0.45
    eng
    0.44
    =""><
    0.40
    amp
    0.39
     उड़
    0.39
     হিসাব
    0.39
     pust
    0.39
    POSITIVE LOGITS
    তীর্থ
    0.48
    Deine
    0.44
    Kamu
    0.44
    Thay
    0.43
    욜
    0.43
    ခံ
    0.43
    вні
    0.43
    해도
    0.42
    Osaka
    0.42
    ћин
    0.41
    Activations Density 0.001%

    No Known Activations