© 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. 145410
    Prev
    Next
    INDEX
    Explanations

    GM, Motor, Belt, exposure, pieces

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

    indicating comfort or options

    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
    O
    0.54
     IV
    0.51
     converged
    0.51
    L
    0.50
     round
    0.50
    ер
    0.49
     bonded
    0.48
     distinct
    0.48
     Hs
    0.48
     centre
    0.48
    POSITIVE LOGITS
     شركات
    0.50
     פרו
    0.50
    כר
    0.48
    覺得
    0.48
    ية
    0.47
    نى
    0.46
    螫
    0.45
    نز
    0.44
    عليه
    0.44
    uzie
    0.43
    Activations Density 0.000%

    No Known Activations