© 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. 97284
    Prev
    Next
    INDEX
    Explanations

    sentence introductions or continuations

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

    opening quotation mark

    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
     mutta
    0.50
    .,"
    0.47
     lakini
    0.46
    ,"
    0.45
     tengas
    0.45
     aswell
    0.45
    ˏ
    0.44
     jälkeen
    0.43
    ,'
    0.42
     lekin
    0.42
    POSITIVE LOGITS
    }.$$
    0.47
     மொத்த
    0.45
     статисти
    0.44
     இந்த
    0.43
     কিছু
    0.42
     те
    0.41
     стали
    0.41
    this
    0.41
     RTI
    0.41
     स्थान
    0.40
    Activations Density 0.019%

    No Known Activations