© 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. 126003
    Prev
    Next
    INDEX
    Explanations

    journal article marker

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

    describes character traits

    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
     segítség
    0.48
    一块
    0.42
    GOOGLE
    0.42
     pavilions
    0.41
     বৃহ
    0.41
    台北
    0.40
    园
    0.40
    Nano
    0.40
     poveć
    0.39
     dode
    0.39
    POSITIVE LOGITS
     urinary
    0.39
    लंघन
    0.38
    
    0.37
    ὗ
    0.36
    ﮩ
    0.36
    ƅ
    0.36
     самой
    0.35
    otoxicity
    0.35
    ुत
    0.34
    🦠
    0.34
    Activations Density 0.002%

    No Known Activations