© 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. 202726
    Prev
    Next
    INDEX
    Explanations

    specific phrases and compounds

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

    profile information

    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
    说
    0.51
    ní
    0.50
     उजा
    0.48
    प्रा
    0.46
    公众
    0.46
    мпания
    0.46
    ：
    0.45
    ünde
    0.45
    ject
    0.44
    ম
    0.44
    POSITIVE LOGITS
     ஏனெ
    0.42
     சுவர்
    0.41
     लिस्ट
    0.40
     ஏனெனில்
    0.40
    unexpected
    0.40
    ariously
    0.40
     заслу
    0.40
    adr
    0.39
     список
    0.39
     გვ
    0.39
    Activations Density 0.001%

    No Known Activations