© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2844
    Prev
    Next
    INDEX
    Explanations

    SQL queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Celestial
    1.18
     Floating
    1.18
     Landmarks
    1.07
     Progression
    1.05
     Cultural
    1.04
     Printable
    1.03
    }));
    1.03
     ሂደት
    1.03
     उधर
    1.02
    ]));
    1.02
    POSITIVE LOGITS
    fortunately
    1.11
    ști
    0.96
    şti
    0.96
    bent
    0.92
     bütün
    0.92
    ண
    0.92
    menin
    0.90
    v
    0.90
    يا
    0.90
    OM
    0.90
    Activations Density 0.000%

    No Known Activations