© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3231
    Prev
    Next
    INDEX
    Explanations

    code block delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     the
    0.54
    囁
    0.49
     Amnesty
    0.48
    the
    0.45
    ↵
    0.44
     xóa
    0.43
     rename
    0.42
    Json
    0.42
    ↵↵
    0.42
    });
    0.42
    POSITIVE LOGITS
    ēi
    0.53
    ǎi
    0.52
    nutrient
    0.51
     fjord
    0.50
    proliferation
    0.50
    ovariant
    0.50
     fasteners
    0.50
    environnement
    0.50
    
    0.49
    strand
    0.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.