© 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. 8335
    Prev
    Next
    INDEX
    Explanations

    numbered lists of strategic concepts

    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
     parameterType
    0.97
    }=
    0.82
    ambique
    0.82
    roweak
    0.81
    oside
    0.80
    othelioma
    0.79
    ~(
    0.78
     বুলেট
    0.78
     thôn
    0.78
    ]("
    0.78
    POSITIVE LOGITS
    Official
    1.74
    official
    1.53
    MT
    1.48
    Offic
    1.43
    REAL
    1.35
    USA
    1.35
     OFFICIAL
    1.34
    __,
    1.34
     Official
    1.33
    Officials
    1.33
    Activations Density 0.143%

    No Known Activations