© 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. 227600
    Prev
    Next
    INDEX
    Explanations

    advice and factual information

    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
     khand
    0.54
    oer
    0.49
     strani
    0.43
     enquire
    0.43
     )}$
    0.43
     enquiries
    0.42
     १४
    0.42
     kte
    0.42
     ""`
    0.42
     itinerant
    0.42
    POSITIVE LOGITS
    ává
    0.46
    Serbia
    0.46
    েরা
    0.45
    サプライ
    0.44
    ی
    0.44
    ácia
    0.44
    ISTAN
    0.44
    即
    0.43
    Kingdom
    0.42
    が必要
    0.42
    Activations Density 0.000%

    No Known Activations