© 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. 49104
    Prev
    Next
    INDEX
    Explanations

    pronouns and possessives

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

    descriptions, definitions, labels

    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
    дри
    0.50
    த்துக்கு
    0.49
     combat
    0.46
     encerr
    0.46
    唕
    0.43
    ributive
    0.43
     guilds
    0.42
    яз
    0.42
    ́t
    0.42
    ");</
    0.42
    POSITIVE LOGITS
    ۰
    0.46
    岁
    0.45
     حصے
    0.44
    hObject
    0.43
    0
    0.43
     HStack
    0.42
     очеред
    0.42
     रिलेशनशिप
    0.41
     giriş
    0.41
    Matcher
    0.40
    Activations Density 0.000%

    No Known Activations