© 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. 169346
    Prev
    Next
    INDEX
    Explanations

    helping or serving others

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

    students who, address the, cities, creativity

    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
    Prz
    0.54
    ቖ
    0.50
    posizione
    0.49
    Dentro
    0.49
    ய்டா
    0.47
     ორგანო
    0.47
    Contacto
    0.47
    ACIÓN
    0.47
     Após
    0.47
     υπάρχ
    0.46
    POSITIVE LOGITS
    sp
    0.49
    oran
    0.49
    س
    0.46
    aw
    0.46
    i
    0.46
    si
    0.45
    oe
    0.44
    she
    0.43
    s
    0.42
    sts
    0.41
    Activations Density 0.001%

    No Known Activations