© 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. 99750
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and following words

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

    multilingual content and specific terms

    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
     yana
    0.46
    ched
    0.45
    oc
    0.43
    jska
    0.43
    3
    0.43
     ===
    0.43
    astava
    0.43
    كذا
    0.43
    1
    0.43
    5
    0.43
    POSITIVE LOGITS
    ת
    0.53
    ר
    0.48
     nombres
    0.48
    耇
    0.47
     focuss
    0.47
     considera
    0.47
     previa
    0.46
     clichés
    0.46
     текста
    0.46
     দুধ
    0.46
    Activations Density 0.000%

    No Known Activations