© 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. 53905
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    GPT-4 introduction points

    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
    Про
    0.50
    К
    0.50
    Express
    0.50
    Velocity
    0.47
    ک
    0.47
    Гу
    0.46
    Histor
    0.44
    য়
    0.44
    CON
    0.44
    Eng
    0.44
    POSITIVE LOGITS
     未
    0.57
     Seit
    0.54
     没有
    0.52
     沒有
    0.51
     西
    0.50
     februari
    0.50
     长
    0.50
     上
    0.49
     decembrie
    0.49
     猫
    0.48
    Activations Density 0.000%

    No Known Activations