© 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. 152498
    Prev
    Next
    INDEX
    Explanations

    acquired skills

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

    changing business or technical details

    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
    usuario
    0.48
    ズニー
    0.46
     litros
    0.44
    о
    0.44
     familiari
    0.43
    udp
    0.43
    overlay
    0.43
     plenary
    0.42
     противопо
    0.42
    य
    0.42
    POSITIVE LOGITS
    adığı
    0.50
     Stadt
    0.45
    毖
    0.45
    实践
    0.44
     Williamsburg
    0.44
    leşt
    0.43
     Müdür
    0.43
     گذر
    0.43
     වැඩ
    0.43
    වුන්
    0.42
    Activations Density 0.001%

    No Known Activations