© 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. 78274
    Prev
    Next
    INDEX
    Explanations

    punctuation or conjunctions

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

    calculations and units

    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
     selectors
    0.52
    蚂
    0.50
    ట్టిన
    0.47
     သူမ
    0.47
     Greetings
    0.46
     タ
    0.45
     অ্যান্টি
    0.45
     แ
    0.44
    𝕤
    0.44
     月
    0.44
    POSITIVE LOGITS
    不是
    0.48
    NEE
    0.48
    ף
    0.45
    לות
    0.45
    енты
    0.44
    ция
    0.44
    اء
    0.44
    enie
    0.43
    னால்
    0.43
    ряда
    0.43
    Activations Density 0.000%

    No Known Activations