© 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. 123327
    Prev
    Next
    INDEX
    Explanations

    multilingual text detection

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

    airspeed of an unladen swallow

    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
     ekspl
    0.48
    ӥ
    0.46
    making
    0.46
    Expl
    0.46
     Individ
    0.45
    肋
    0.45
     coats
    0.44
     brach
    0.44
    manufact
    0.43
     Explicit
    0.42
    POSITIVE LOGITS
    ched
    0.49
     시간을
    0.48
     गिलास
    0.47
     তালিকায়
    0.45
     हिरासत
    0.44
     لیست
    0.44
    iles
    0.44
     请
    0.44
     persuaded
    0.44
    дила
    0.44
    Activations Density 0.000%

    No Known Activations