© 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. 37772
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    after user request

    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
    the
    0.43
    The
    0.41
     The
    0.40
    centric
    0.39
    popular
    0.38
     celebrated
    0.37
     Valley
    0.37
    ↵↵
    0.37
    G
    0.37
     Veterans
    0.36
    POSITIVE LOGITS
     theseKeys
    0.46
     operands
    0.44
     tuple
    0.43
     />}
    0.42
     amplitudes
    0.42
     函数
    0.42
     nonEmpty
    0.41
     Chebyshev
    0.41
     scrollBody
    0.40
     tensors
    0.40
    Activations Density 0.026%

    No Known Activations