© 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. 208929
    Prev
    Next
    INDEX
    Explanations

    traffic from, health and, affiliate made

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

    backup contingency or abilities

    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
    with
    0.53
     Square
    0.51
     End
    0.50
    Images
    0.49
     Reading
    0.48
     ©
    0.47
    Square
    0.46
     Economic
    0.46
     Scientific
    0.46
     Financial
    0.46
    POSITIVE LOGITS
    勇
    0.51
    誓
    0.48
     consacré
    0.47
    傍
    0.45
     compagn
    0.44
    Berikut
    0.44
    贼
    0.44
    マネ
    0.44
     sobreviv
    0.44
    、“
    0.43
    Activations Density 0.005%

    No Known Activations