© 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. 90191
    Prev
    Next
    INDEX
    Explanations

    documentary series information

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

    potentially, endurance, company, MT, side

    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
    从未
    0.46
     prev
    0.44
    大师
    0.44
     B
    0.43
    other
    0.42
     G
    0.42
     critic
    0.42
     தெ
    0.41
     coeff
    0.41
    teres
    0.40
    POSITIVE LOGITS
    volent
    0.48
    ("*
    0.46
    것
    0.46
    䒺
    0.46
    르게
    0.45
    꿍
    0.45
    ائم
    0.45
     semaines
    0.45
    क्यूमेंट
    0.45
     المال
    0.44
    Activations Density 0.000%

    No Known Activations