© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7982
    Prev
    Next
    INDEX
    Explanations

    believing, receiving, acknowledging, revealing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_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
    투
    1.02
     இதே
    0.97
    рис
    0.92
    explos
    0.89
    beau
    0.89
    fresh
    0.89
    jis
    0.87
    Cxt
    0.87
    туру
    0.87
     करण्याचे
    0.86
    POSITIVE LOGITS
    ieving
    1.12
    ongs
    0.99
    ieved
    0.98
    晓
    0.92
     Pob
    0.89
     Pen
    0.89
     Parrish
    0.87
    曉
    0.86
    ieves
    0.85
    ievable
    0.85
    Activations Density 0.038%

    No Known Activations