© 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. 180846
    Prev
    Next
    INDEX
    Explanations

    pronoun/noun/number followed by verb/noun/preposition

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

    cover their, algae bloom, Total Track

    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
     activities
    0.46
     কার্যকলাপ
    0.44
    activities
    0.44
    Activities
    0.43
     ACTIVITIES
    0.43
    璉
    0.42
     जलवायु
    0.41
     activiteiten
    0.41
     Activities
    0.40
     Accessory
    0.40
    POSITIVE LOGITS
    ీ
    0.53
    ade
    0.47
     sì
    0.47
    iem
    0.45
     encima
    0.45
    bnf
    0.44
    ليز
    0.43
    nytimes
    0.42
    }/
    0.42
    idze
    0.42
    Activations Density 0.002%

    No Known Activations