© 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. 228631
    Prev
    Next
    INDEX
    Explanations

    server, network, terms, year

    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
    습니다
    0.50
    ӗ
    0.48
    amata
    0.46
    ěji
    0.46
     maîtr
    0.46
    쁩
    0.45
    āo
    0.45
    ponible
    0.45
    ందన్నారు
    0.45
     triumphant
    0.44
    POSITIVE LOGITS
     wilderness
    0.46
     gne
    0.43
     and
    0.43
    S
    0.43
    O
    0.43
     furl
    0.42
     skid
    0.42
     formate
    0.42
     snd
    0.41
     met
    0.41
    Activations Density 0.000%

    No Known Activations