© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127863
    Prev
    Next
    INDEX
    Explanations

    python code

    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
     Young
    0.46
    쳥
    0.46
     environmental
    0.45
     Principles
    0.44
    夗
    0.44
     principles
    0.44
    飽
    0.44
     Children
    0.43
     ambiental
    0.41
    员
    0.41
    POSITIVE LOGITS
    aih
    0.47
    lamydia
    0.44
    Exist
    0.43
     दुष्
    0.43
    akit
    0.43
    Dirac
    0.43
    quantum
    0.42
     суще
    0.41
    inafter
    0.41
     اعظم
    0.41
    Activations Density 0.003%

    No Known Activations