© 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. 146035
    Prev
    Next
    INDEX
    Explanations

    recent appellate decisions

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

    stop or continue

    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
    ed
    0.54
     పదార్థ
    0.50
    e
    0.49
    тери
    0.47
     ආහාර
    0.46
     pracovní
    0.46
     fucked
    0.45
    UAL
    0.45
     файлы
    0.45
    ૫
    0.44
    POSITIVE LOGITS
     clôt
    0.51
     discontinuities
    0.44
     laiss
    0.44
     orthogon
    0.42
    ształ
    0.41
     Osp
    0.41
     discontinuity
    0.41
    の大
    0.40
    入れて
    0.40
     imper
    0.39
    Activations Density 0.000%

    No Known Activations