© 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. 229208
    Prev
    Next
    INDEX
    Explanations

    leaders or renovated

    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
    ೇಶ್
    0.52
     fatalities
    0.51
    ラ
    0.50
     unification
    0.49
    トマト
    0.49
    SERVIDOR
    0.48
    給大家
    0.48
     víctimas
    0.47
    އް
    0.47
     LEN
    0.47
    POSITIVE LOGITS
    orr
    0.49
    ite
    0.47
    ik
    0.44
    achter
    0.43
    uk
    0.43
    itet
    0.42
    传染
    0.42
    á
    0.42
    aire
    0.41
    ār
    0.41
    Activations Density 0.000%

    No Known Activations