© 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. 26309
    Prev
    Next
    INDEX
    Explanations

    descriptive phrases following words

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

    code with parameters

    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
    Removing
    0.47
    TA
    0.46
    。
    0.46
    TE
    0.46
    ฟ
    0.46
    忔
    0.46
    ᄌ
    0.45
    ็ว
    0.44
    忓
    0.44
    ᄅ
    0.44
    POSITIVE LOGITS
     harbours
    0.50
     Kamala
    0.48
     possano
    0.47
     hospitality
    0.47
     cinque
    0.47
     trovano
    0.46
     kiosks
    0.46
     twilight
    0.46
     shelved
    0.45
     overlooks
    0.45
    Activations Density 0.000%

    No Known Activations