© 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. 86428
    Prev
    Next
    INDEX
    Explanations

    find great beautiful results

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

    scenario and content discovery

    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
    和社会
    0.53
    প্রবাসী
    0.51
    顾
    0.48
    वाद
    0.48
    茼
    0.47
    浾
    0.45
     тера
    0.45
     політи
    0.45
     அழுத்த
    0.45
    哞
    0.45
    POSITIVE LOGITS
     find
    0.48
    find
    0.48
    }_{
    0.46
     haird
    0.46
     lze
    0.45
     }}
    0.44
     sly
    0.44
    pecies
    0.44
     unleashing
    0.44
     morph
    0.44
    Activations Density 0.001%

    No Known Activations