© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 170724
    Prev
    Next
    INDEX
    Explanations

    predicting following words

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

    technical engineering or heads

    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
    Negative Logits
     puntu
    0.45
     straws
    0.45
     sabbam
    0.43
    ,_-
    0.42
     subtiliter
    0.42
    DURATION
    0.42
     przer
    0.42
     defrost
    0.42
    رحبا
    0.42
     tay
    0.41
    POSITIVE LOGITS
    2
    0.56
    in
    0.54
    iller
    0.50
     данни
    0.50
     CRO
    0.49
    Cntr
    0.49
    1
    0.49
    oller
    0.48
     言っ
    0.47
     कटोच
    0.47
    Activations Density 0.001%

    No Known Activations