© 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. 213046
    Prev
    Next
    INDEX
    Explanations

    words forming common phrases

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

    descriptive compound nouns

    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
    \%),
    0.43
    arının
    0.41
     microorganisms
    0.39
    டும்
    0.38
    2
    0.38
    अपनी
    0.38
     disposición
    0.37
    elerinin
    0.36
    észeti
    0.36
     প্রচুর
    0.36
    POSITIVE LOGITS
     vrai
    0.48
    ጀ
    0.40
     ب
    0.39
    iniai
    0.38
     ლ
    0.38
    hme
    0.37
    ien
    0.37
     मॅ
    0.37
     മറ്റ്
    0.37
    ie
    0.37
    Activations Density 0.114%

    No Known Activations