© 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. 53-GEMMASCOPE-2-RES-65K
    7. 7916
    Prev
    Next
    INDEX
    Explanations

    names ending in ana or ina

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

    vicuna models

    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
    суль
    0.45
    Added
    0.44
    ±
    0.43
    chodu
    0.43
     +/-
    0.43
    Assess
    0.41
    +/-
    0.41
     ±
    0.38
    Occasionally
    0.38
    
    0.38
    POSITIVE LOGITS
    issance
    0.82
    ively
    0.56
    issances
    0.51
    チュラル
    0.51
    쁜
    0.49
     whole
    0.47
     втором
    0.45
    esthesia
    0.44
    ряду
    0.44
    weza
    0.42
    Activations Density 0.040%

    No Known Activations