© 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. 161424
    Prev
    Next
    INDEX
    Explanations

    hunting for

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

    exceeding scope or expectations

    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
     itt
    0.48
    dm
    0.46
     Donald
    0.46
     buch
    0.45
     n
    0.45
     nev
    0.44
     le
    0.43
     m
    0.43
     kem
    0.42
     dm
    0.42
    POSITIVE LOGITS
    φή
    0.52
    뻣
    0.51
     紹介
    0.51
    irrah
    0.48
    ⟹
    0.47
    нему
    0.46
    ᾳ
    0.45
    ოკ
    0.45
    aphore
    0.45
     없음
    0.44
    Activations Density 0.001%

    No Known Activations