© 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-16K
    7. 8684
    Prev
    Next
    INDEX
    Explanations

    code formatting and data structures

    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_16k_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
    一定的
    0.43
     not
    0.42
    use
    0.41
    necessary
    0.39
    ounded
    0.39
    2
    0.39
    correct
    0.38
    职
    0.38
    0
    0.38
     be
    0.38
    POSITIVE LOGITS
     fgets
    0.45
     them
    0.44
     của
    0.44
     ĝi
    0.43
    গি
    0.42
     उन्‍ह
    0.40
     theses
    0.40
    them
    0.39
     carinatis
    0.39
    нской
    0.38
    Activations Density 0.159%

    No Known Activations