© 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. 129376
    Prev
    Next
    INDEX
    Explanations

    companies throughout

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

    SQL injection and other specific syntaxes

    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
    muscle
    0.48
     sweet
    0.46
     B
    0.45
     equate
    0.45
     hash
    0.45
     cling
    0.45
     Russell
    0.44
     ICRC
    0.44
     Jason
    0.43
     valence
    0.43
    POSITIVE LOGITS
     próximas
    0.53
    
    0.49
     gespre
    0.49
     próxima
    0.49
    лябин
    0.48
    día
    0.48
    ngày
    0.47
    惘
    0.47
     amplio
    0.46
     lét
    0.46
    Activations Density 0.001%

    No Known Activations