© 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. 226020
    Prev
    Next
    INDEX
    Explanations

    marketers that, starting to

    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
     dame
    0.50
    URCH
    0.49
     giz
    0.48
    ravity
    0.48
     Kč
    0.48
    仁
    0.48
     neki
    0.47
     स्ने
    0.45
     otros
    0.45
     DENUMIRE
    0.45
    POSITIVE LOGITS
    Begin
    0.44
    {
    0.44
     ascends
    0.43
    자리
    0.42
    Agr
    0.40
     consolid
    0.40
     agr
    0.40
     bimod
    0.40
    िपल
    0.40
    (&
    0.39
    Activations Density 0.001%

    No Known Activations