© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 37044
    Prev
    Next
    INDEX
    Explanations

    media and roles

    np_acts-logits-general · gemini-2.5-flash-lite

    intervals or training

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    いた
    0.57
    だい
    0.55
    пя
    0.52
    ты
    0.51
    き
    0.51
    に行
    0.50
    사를
    0.50
    にする
    0.49
    Кто
    0.49
    کس
    0.48
    POSITIVE LOGITS
    er
    0.52
    -)
    0.52
     Accountant
    0.48
     accountant
    0.45
    ership
    0.44
     Schedule
    0.43
    Prescott
    0.43
    FP
    0.42
     leaflets
    0.42
     Championships
    0.41
    Activations Density 0.000%

    No Known Activations