© 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. 74822
    Prev
    Next
    INDEX
    Explanations

    month names and time periods

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

    block services mining

    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
     Séb
    0.51
    ollow
    0.49
    ő
    0.49
    кров
    0.48
    issel
    0.48
    કિસ્તા
    0.47
    𝐜
    0.47
    िब
    0.46
    สัง
    0.46
    قيم
    0.46
    POSITIVE LOGITS
     fertilizer
    0.51
    вого
    0.48
     shelf
    0.46
    oxyphenyl
    0.46
     environmental
    0.44
     pfl
    0.44
     horarios
    0.44
     restricted
    0.43
     devo
    0.43
     replaceable
    0.42
    Activations Density 0.000%

    No Known Activations