© 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. 131059
    Prev
    Next
    INDEX
    Explanations

    brand development

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

    engineering, healthcare, digital, investigations

    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
    ub
    0.53
    kha
    0.50
    kin
    0.49
    via
    0.49
    irii
    0.48
    </i>
    0.47
    ographs
    0.47
     },
    0.47
    ၊
    0.46
    views
    0.46
    POSITIVE LOGITS
    Dü
    0.47
    的神
    0.46
     newlyweds
    0.46
     componenti
    0.45
    Clic
    0.45
     yorum
    0.43
     vrijed
    0.43
     stupe
    0.43
     satell
    0.43
     prodotti
    0.42
    Activations Density 0.000%

    No Known Activations