© 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. 202117
    Prev
    Next
    INDEX
    Explanations

    specifications or announcements

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

    regarding analysis sum log historical

    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
    ásico
    0.45
    がたくさん
    0.45
    の人
    0.45
     पीपल
    0.45
    していきます
    0.44
     accelerator
    0.44
    𝗴
    0.43
    と思いました
    0.43
    کسی
    0.43
    ៤
    0.42
    POSITIVE LOGITS
     an
    0.49
    ્સ
    0.49
    ט
    0.48
    掎
    0.47
     Profes
    0.46
    驹
    0.46
        
    0.45
    يت
    0.45
    ení
    0.44
    裕
    0.44
    Activations Density 0.000%

    No Known Activations