© 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. 51430
    Prev
    Next
    INDEX
    Explanations

    longest, outcomes, December, cases

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

    JSON action objects

    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
    牷
    0.55
    SACTION
    0.54
     పే
    0.50
    芓
    0.50
    Noun
    0.50
    리
    0.50
    Macrophages
    0.49
    窨
    0.49
    原子炉
    0.49
    絭
    0.48
    POSITIVE LOGITS
     I
    0.63
     Müller
    0.55
     M
    0.52
     e
    0.51
     C
    0.51
     de
    0.49
     A
    0.49
     E
    0.48
     MRT
    0.48
     S
    0.48
    Activations Density 0.000%

    No Known Activations