© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 9856
    Prev
    Next
    INDEX
    Explanations

    hyphenated prefixes and suffixes

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

    CSV files, text generation

    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
    ()/
    0.51
    ˋ
    0.48
     /
    0.46
     قر
    0.46
    /_
    0.46
    შვ
    0.46
    犹如
    0.45
     ú
    0.45
    /"
    0.44
     उपनिवेश
    0.44
    POSITIVE LOGITS
    𝘇
    0.51
    ουν
    0.51
     enrolling
    0.50
    s
    0.48
     evaluating
    0.47
     meters
    0.47
     agreeing
    0.47
     educating
    0.45
     officially
    0.45
     dlatego
    0.44
    Activations Density 0.000%

    No Known Activations