© 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. 136646
    Prev
    Next
    INDEX
    Explanations

    integers and COUNT

    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
    约
    0.46
    ุ
    0.46
    భవ
    0.45
    تاز
    0.42
    dto
    0.41
    续
    0.40
    驻
    0.40
    Substring
    0.39
    pecting
    0.39
    ]#
    0.38
    POSITIVE LOGITS
     これは
    0.52
     transmit
    0.50
     simulate
    0.50
     Isso
    0.47
     ventil
    0.46
     scream
    0.46
     boost
    0.46
     emitters
    0.46
     inim
    0.45
     tremble
    0.45
    Activations Density 0.001%

    No Known Activations