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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1454
    Prev
    Next
    INDEX
    Explanations

    pic followed by word parts

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

    Vicuna

    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
     topl
    0.40
     ഓൺലൈ
    0.39
     harmonics
    0.38
    TorpedoStore
    0.38
    𒈾
    0.38
    Ἥ
    0.38
    ETHOD
    0.37
     참조
    0.37
    ⿷
    0.37
    デジタル
    0.37
    POSITIVE LOGITS
     twitter
    1.22
    twitter
    1.20
     pic
    1.16
    Twitter
    1.09
     Twitter
    1.06
    pic
    1.00
    ツイ
    1.00
     tweet
    0.94
     টুই
    0.92
    Pic
    0.88
    Activations Density 0.010%

    No Known Activations