© 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. 23389
    Prev
    Next
    INDEX
    Explanations

    gas powered

    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
    rául
    0.50
    㳳
    0.49
    ottam
    0.47
    pyraz
    0.46
     ត
    0.45
    句話
    0.45
    起床
    0.45
    嚧
    0.44
    stä
    0.44
    houden
    0.44
    POSITIVE LOGITS
    3
    0.63
    6
    0.53
     anonymous
    0.52
    4
    0.48
    5
    0.47
    7
    0.46
     flatten
    0.43
    8
    0.43
     research
    0.42
     clean
    0.42
    Activations Density 0.002%

    No Known Activations