© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9577
    Prev
    Next
    INDEX
    Explanations

    word to the wise

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

    word order and problems

    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_40_width_16k_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
     headlines
    0.43
    accord
    0.43
     name
    0.43
    namen
    0.41
    邗
    0.41
     earths
    0.41
     adhesions
    0.41
     Corps
    0.41
     Callie
    0.41
    名称
    0.40
    POSITIVE LOGITS
    िक्ट
    0.57
    spoken
    0.52
     spoken
    0.46
    mith
    0.45
     WORD
    0.43
     এজন্য
    0.43
     uttered
    0.43
    asamb
    0.42
    彙
    0.42
    ার্থ
    0.42
    Activations Density 0.082%

    No Known Activations