© 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. 116171
    Prev
    Next
    INDEX
    Explanations

    over Goals

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

    Object Class

    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
    SHA
    0.47
    º
    0.44
    Seriously
    0.40
    Fellow
    0.40
    Communic
    0.40
    EM
    0.40
    ̱
    0.40
    Zombie
    0.40
    COMP
    0.39
    <0xDB>
    0.39
    POSITIVE LOGITS
     Neuer
    0.48
     পরিবর্তনের
    0.46
     déplacement
    0.43
     desloc
    0.41
     If
    0.40
    वैसे
    0.40
     displaced
    0.40
     spør
    0.40
     nejs
    0.39
     নিমিত
    0.39
    Activations Density 0.002%

    No Known Activations