© 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. 49913
    Prev
    Next
    INDEX
    Explanations

    blaze fled

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

    introduces or describes relationships

    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
     Beziehungen
    0.50
     العلاقات
    0.45
    ദേ
    0.45
    荨
    0.44
     Gespr
    0.44
     dicembre
    0.43
     allocations
    0.43
     blouses
    0.43
     apartamentos
    0.43
     legnagyobb
    0.42
    POSITIVE LOGITS
    RootDir
    0.50
    r
    0.49
    Server
    0.49
    sword
    0.49
     patterning
    0.46
    GUN
    0.45
    Sword
    0.45
    PA
    0.45
    Clar
    0.45
    走行
    0.44
    Activations Density 0.000%

    No Known Activations