© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3092
    Prev
    Next
    INDEX
    Explanations

    specifying technical terms

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

    Russian punctuation and common words

    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_53_width_65k_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
     pptn
    0.44
    [multimodal]
    0.43
     düşünüyorum
    0.43
     ডিজাই
    0.41
     මෙය
    0.41
    帳に追加
    0.40
    子公司
    0.40
    揶
    0.40
    世界上
    0.39
     benutzer
    0.39
    POSITIVE LOGITS
    yt
    0.50
    j
    0.45
    h
    0.43
    li
    0.43
    he
    0.43
    ()
    0.42
     I
    0.41
    me
    0.41
    SC
    0.41
     Ang
    0.40
    Activations Density 0.062%

    No Known Activations