© 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. 199717
    Prev
    Next
    INDEX
    Explanations

    collocations following common words

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

    mineral applications, rigorous quality

    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
    ör
    0.48
    urn
    0.46
    student
    0.46
    ivers
    0.46
     is
    0.45
    um
    0.45
    ó
    0.45
    org
    0.44
    üt
    0.44
    ypress
    0.44
    POSITIVE LOGITS
    ሦ
    0.52
     onboarding
    0.45
     воздух
    0.45
    Relationships
    0.45
    тила
    0.44
    棻
    0.44
    瘓
    0.44
     allowances
    0.44
    攤
    0.43
    辇
    0.43
    Activations Density 0.000%

    No Known Activations