© 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. 135000
    Prev
    Next
    INDEX
    Explanations

    identification information

    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
    亚
    0.46
    อย่าง
    0.46
    very
    0.45
    fully
    0.44
    য়
    0.43
    亞
    0.43
    дою
    0.43
    Tyr
    0.42
    https
    0.42
    and
    0.41
    POSITIVE LOGITS
     reeks
    0.49
    윕
    0.49
     kwaliteit
    0.48
     Strukt
    0.48
     Dhaka
    0.47
     ocasião
    0.47
     போன்றவை
    0.47
    訌
    0.46
    дентификаторы
    0.46
    ToReference
    0.45
    Activations Density 0.001%

    No Known Activations