© 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. 251415
    Prev
    Next
    INDEX
    Explanations

    attention, return, increase

    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
    jed
    0.46
    一线
    0.46
    ili
    0.45
    oni
    0.44
    äß
    0.42
    ury
    0.42
    .|
    0.41
    imy
    0.41
    nier
    0.41
     വഴി
    0.40
    POSITIVE LOGITS
    גו
    0.52
     strcat
    0.44
     অঞ্চ
    0.44
     Güzel
    0.44
    ברים
    0.43
     addressing
    0.43
     addr
    0.43
     administering
    0.43
    ፓ
    0.43
     আসিল
    0.43
    Activations Density 0.002%

    No Known Activations