© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4773
    Prev
    Next
    INDEX
    Explanations

    Frameworks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     leachate
    0.32
    魉
    0.32
    তাসীন
    0.31
     ordinate
    0.30
     みたい
    0.30
     alkene
    0.30
    ێنی
    0.29
     conjugacy
    0.29
    ⸩
    0.29
     magnon
    0.29
    POSITIVE LOGITS
    The
    0.48
    If
    0.45
    While
    0.43
    For
    0.42
    One
    0.41
    Before
    0.41
    In
    0.40
    When
    0.40
    As
    0.40
    C
    0.39
    Activations Density 0.000%

    No Known Activations