© 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. 128101
    Prev
    Next
    INDEX
    Explanations

    Spanish speakers

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

    hidden feature

    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
     ―
    0.50
     numeracy
    0.47
     trailbl
    0.46
     Compton
    0.46
    geri
    0.45
    .•
    0.45
    懟
    0.45
     woody
    0.44
     Europas
    0.44
     dolphins
    0.44
    POSITIVE LOGITS
    Ck
    0.51
    ToCheck
    0.47
    isIn
    0.46
    nok
    0.45
    Anybody
    0.45
    It
    0.43
    To
    0.43
    losses
    0.43
    taxes
    0.43
    ন
    0.43
    Activations Density 0.001%

    No Known Activations