© 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. 40502
    Prev
    Next
    INDEX
    Explanations

    originally intended

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

    new, must, section, for

    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
    )$$
    0.51
    后面
    0.50
    ıyorum
    0.47
    劳
    0.47
    njih
    0.47
     Цу
    0.47
     zove
    0.46
    infty
    0.46
    kowy
    0.46
     kohta
    0.45
    POSITIVE LOGITS
    튿
    0.48
     eat
    0.46
     dolphins
    0.45
     detrimental
    0.44
     destructive
    0.43
     anti
    0.42
     polyethylene
    0.42
     antir
    0.42
     eating
    0.42
     gastroenter
    0.41
    Activations Density 0.000%

    No Known Activations