© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4676
    Prev
    Next
    INDEX
    Explanations

    enumerated options

    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
    ا۔
    1.71
    یں۔
    1.67
    ے۔
    1.58
     گا۔
    1.52
    .’
    1.51
    ’.
    1.51
    .
    1.47
     گی۔
    1.43
    .’’
    1.42
    ماس
    1.41
    POSITIVE LOGITS
    avadoc
    1.20
     Toxicol
    1.13
    腋
    1.13
     Aldi
    1.12
     Okanagan
    1.08
     Aur
    1.08
     highScore
    1.04
     ethylene
    1.00
     estrogen
    0.99
     Gris
    0.99
    Activations Density 0.022%

    No Known Activations