© 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. 87735
    Prev
    Next
    INDEX
    Explanations

    adoption and release

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

    commands and technical terms

    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
    बार
    0.52
     בו
    0.51
    vish
    0.50
     מל
    0.50
     उधार
    0.47
     برابر
    0.47
    मॉन
    0.47
     ה
    0.46
    薁
    0.46
     গেলাম
    0.46
    POSITIVE LOGITS
     rep
    0.44
     enterprising
    0.44
     itertools
    0.43
     triang
    0.42
     hypertrophy
    0.41
     brid
    0.41
    তিক
    0.39
     astronomical
    0.39
     rospy
    0.38
     gypsy
    0.38
    Activations Density 0.000%

    No Known Activations