© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11995
    Prev
    Next
    INDEX
    Explanations

    walk to or tours

    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_7_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
    áját
    2.07
    enary
    2.06
    nog
    1.98
    niji
    1.94
    ený
    1.93
    teni
    1.92
    𝙚
    1.89
    ्स
    1.86
    braio
    1.84
    𝙝
    1.83
    POSITIVE LOGITS
    ﻝ
    2.46
    <bos>
    2.43
     επο
    2.31
     cohorts
    2.13
     instructions
    2.00
     directions
    1.99
     Portage
    1.98
     locations
    1.95
     unfold
    1.94
     options
    1.94
    Activations Density 0.043%

    No Known Activations