© 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. 4581
    Prev
    Next
    INDEX
    Explanations

    community support and questions

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

    speech act recognition

    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
    ᥙ
    0.21
    <unused2162>
    0.20
     tuples
    0.20
     shader
    0.20
    <unused2137>
    0.20
    <unused100>
    0.19
    <unused324>
    0.19
     vila
    0.19
     libid
    0.19
    শ্ম
    0.18
    POSITIVE LOGITS
     *
    0.27
     
    0.25
    ↵↵
    0.24
     (
    0.24
     •
    0.24
    ----------------
    0.23
     
    0.23
     Перейти
    0.22
     \*
    0.22
     |
    0.22
    Activations Density 0.332%

    No Known Activations