© 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. 148497
    Prev
    Next
    INDEX
    Explanations

    specific words following common words

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

    discussion topics

    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
     מש
    0.49
     כל
    0.49
    seriously
    0.49
     ఆలో
    0.48
     בני
    0.46
    ological
    0.45
    ל
    0.45
     مرتبط
    0.43
     ثانيه
    0.43
    ְ
    0.43
    POSITIVE LOGITS
    fetchall
    0.48
    u
    0.47
     Jamestown
    0.44
     postnatal
    0.44
     decedent
    0.44
     cashier
    0.43
     proximal
    0.43
     Bedford
    0.43
     Metallica
    0.42
     pastor
    0.41
    Activations Density 0.002%

    No Known Activations