© 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. 3853
    Prev
    Next
    INDEX
    Explanations

    by + method or agent

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

    by followed by action

    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
    म
    0.28
    м
    0.24
    ية
    0.24
    </td>
    0.23
    ר
    0.23
    م
    0.22
    ன்
    0.22
    ാ
    0.22
     والم
    0.21
     ၁
    0.21
    POSITIVE LOGITS
     dint
    0.32
     virtue
    0.30
    zantine
    0.25
     вда
    0.22
     този
    0.22
     inserting
    0.22
     всё
    0.21
     дизайн
    0.21
     creating
    0.21
     resorting
    0.21
    Activations Density 0.514%

    No Known Activations