© 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. 24052
    Prev
    Next
    INDEX
    Explanations

    apply, peruse, hesitate, email, aim

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

    universal word

    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
    d
    0.57
    t
    0.53
    i
    0.49
    ኼ
    0.47
    h
    0.46
    us
    0.45
     splend
    0.45
     richieste
    0.45
    '
    0.45
    Х
    0.45
    POSITIVE LOGITS
    俺
    0.46
     नाही
    0.44
    WIRE
    0.43
     चैलेंज
    0.43
    DEBUGFS
    0.42
     俺
    0.42
     इति
    0.42
     กู
    0.42
    还是要
    0.42
     Quỳnh
    0.42
    Activations Density 0.001%

    No Known Activations