© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 193614
    Prev
    Next
    INDEX
    Explanations

    Nova Scotia, basically read

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

    changes and states

    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
    burgo
    0.54
    印象
    0.49
    Notre
    0.45
    nahi
    0.45
    UAE
    0.44
    Gruntfile
    0.44
    ionista
    0.44
    瞠
    0.43
    ρύ
    0.43
    rire
    0.42
    POSITIVE LOGITS
     JC
    0.52
     возник
    0.50
     возника
    0.50
     altered
    0.50
     Artikel
    0.49
     amendments
    0.49
     amended
    0.48
     Tas
    0.46
     alterations
    0.46
     TDS
    0.46
    Activations Density 0.000%

    No Known Activations