© 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. 227775
    Prev
    Next
    INDEX
    Explanations

    common punctuation and words

    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
     Fortaleza
    0.55
     októ
    0.50
     Afrique
    0.48
    ("@
    0.47
     González
    0.47
     África
    0.46
    数十
    0.46
    ítica
    0.45
    藁
    0.45
    ),
    0.44
    POSITIVE LOGITS
    ה
    0.52
    낌
    0.45
    ווע
    0.45
    ለያዩ
    0.45
    सम
    0.44
     fucking
    0.44
    jamin
    0.44
     damn
    0.44
     prescription
    0.44
    feier
    0.44
    Activations Density 0.001%

    No Known Activations