© 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-16K
    7. 13181
    Prev
    Next
    INDEX
    Explanations

    demonstrative pronouns and descriptors

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

    of this

    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_16k_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
    apeutic
    0.43
    ydney
    0.39
     এবার
    0.39
    PARATION
    0.38
     ಸರ್ಕಾರದ
    0.38
     deliberations
    0.37
    畩
    0.37
     ការ
    0.36
    㬶
    0.36
    ARCH
    0.35
    POSITIVE LOGITS
     tohoto
    0.85
     этого
    0.85
     цієї
    0.83
     данного
    0.82
     dieser
    0.81
     этой
    0.80
     цього
    0.76
     tomto
    0.75
     této
    0.75
     συγκεκρι
    0.75
    Activations Density 0.558%

    No Known Activations