© 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. 69806
    Prev
    Next
    INDEX
    Explanations

    business opportunities

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

    process and data science

    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
    নু
    0.47
    魷
    0.46
    apanam
    0.45
     우리가
    0.44
     আমরা
    0.43
     ہمیں
    0.43
    আমরা
    0.43
    వ్
    0.42
     सरिया
    0.42
    鈦
    0.42
    POSITIVE LOGITS
     masch
    0.55
     opsi
    0.54
     halten
    0.49
     varie
    0.48
     foliis
    0.48
     portals
    0.48
     nummer
    0.47
     valido
    0.47
     dosy
    0.47
     rôle
    0.47
    Activations Density 0.001%

    No Known Activations