© 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. 143255
    Prev
    Next
    INDEX
    Explanations

    education and good deeds

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

    authority said

    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
     대하여
    0.44
     transcription
    0.44
    <sub>
    0.42
     molecular
    0.42
    <sup>
    0.41
     तरंग
    0.41
     deposited
    0.41
     curioso
    0.40
    ँग
    0.40
     exclaimed
    0.40
    POSITIVE LOGITS
     образование
    0.51
    楖
    0.47
    合适
    0.46
    汋
    0.46
    㩽
    0.45
    真正的
    0.45
    也不会
    0.45
    조건
    0.45
    很好的
    0.44
    أي
    0.44
    Activations Density 0.004%

    No Known Activations