© 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. 134108
    Prev
    Next
    INDEX
    Explanations

    source: or described text

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

    sequences starting with 'sequ'

    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
    పురం
    0.47
     alot
    0.44
     bitmaps
    0.43
     দলটি
    0.42
    𝜌
    0.42
    ຂອງ
    0.41
     pratic
    0.41
     поса
    0.41
     inscrito
    0.40
     ejecuta
    0.40
    POSITIVE LOGITS
     neue
    0.47
    ளையும்
    0.44
     Januari
    0.43
    澱
    0.43
     tacit
    0.42
    verkehr
    0.42
     وتح
    0.42
    leistungen
    0.41
    ദാ
    0.41
     richtige
    0.41
    Activations Density 0.005%

    No Known Activations