© 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. 107010
    Prev
    Next
    INDEX
    Explanations

    AP subject courses

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

    Early pioneers

    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
    את
    0.46
    环
    0.46
    贾
    0.43
    тацию
    0.43
     adjournment
    0.43
    nél
    0.43
     тө
    0.43
    ્લે
    0.43
    消失
    0.42
    誅
    0.42
    POSITIVE LOGITS
     aureus
    0.51
    ovable
    0.50
     ingrained
    0.50
    having
    0.50
     ancora
    0.49
     avoir
    0.49
     ayant
    0.48
    commonly
    0.47
     anni
    0.45
    avoir
    0.45
    Activations Density 0.000%

    No Known Activations