© 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. 7915
    Prev
    Next
    INDEX
    Explanations

    information necessary, statisticians, serial bus

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

    German compound 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
    ѣ
    0.38
    ise
    0.38
     valour
    0.38
    쳐
    0.37
    ize
    0.37
    oléon
    0.37
     Database
    0.36
     甲
    0.36
    
    0.36
     saisi
    0.36
    POSITIVE LOGITS
    rahmen
    0.63
    papier
    0.61
    satz
    0.60
    artige
    0.59
    bereitung
    0.59
    folger
    0.58
    platten
    0.58
    nehmer
    0.57
    wissenschaft
    0.57
    wirkung
    0.57
    Activations Density 0.010%

    No Known Activations