© 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. 46958
    Prev
    Next
    INDEX
    Explanations

    conveys imitation limit captures

    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
     japonesa
    0.43
    $&
    0.42
    始まる
    0.41
     cliche
    0.39
     shadowed
    0.39
     tractable
    0.38
    jaan
    0.37
     religiosa
    0.37
     tanto
    0.37
    ститу
    0.37
    POSITIVE LOGITS
    Retour
    0.54
    ANT
    0.50
     histoires
    0.50
    𝗺
    0.50
    Alarm
    0.49
     coût
    0.48
    ્રોલ
    0.48
    𝑅
    0.47
     архів
    0.47
    ORA
    0.47
    Activations Density 0.002%

    No Known Activations