© 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. 152395
    Prev
    Next
    INDEX
    Explanations

    settlers and settling

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

    Often under-resourced, specific, Victorian

    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
     pomoc
    0.56
    顿
    0.52
     Offline
    0.47
     byť
    0.44
     č
    0.44
    زم
    0.44
    ಟನೆ
    0.43
    近
    0.43
    暴露
    0.42
     nóng
    0.42
    POSITIVE LOGITS
     perencanaan
    0.48
     sempl
    0.47
     photograph
    0.47
    
    0.45
    вчи
    0.45
    спу
    0.45
     ühe
    0.44
     pice
    0.43
    CodeableConcept
    0.42
    வாகும்
    0.42
    Activations Density 0.000%

    No Known Activations