© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 5160
    Prev
    Next
    INDEX
    Explanations

    rasped voice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     Fingers
    1.97
     Immune
    1.80
    리즈
    1.78
     chiller
    1.76
     Espírito
    1.72
    푼
    1.67
    subfloat
    1.66
    ][/
    1.65
     transmembrane
    1.64
     Equatorial
    1.62
    POSITIVE LOGITS
     Алек
    1.29
    dawn
    1.26
    ルフ
    1.26
    including
    1.24
    listed
    1.23
    noons
    1.22
    entimes
    1.19
    хран
    1.19
    oners
    1.17
    cludes
    1.17
    Activations Density 0.000%

    No Known Activations