© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 36251
    Prev
    Next
    INDEX
    Explanations

    transfer back

    np_acts-logits-general · gemini-2.5-flash-lite

    considerations and nuances

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    '
    0.51
     concatenation
    0.47
     EPS
    0.46
     mmf
    0.46
     piattaforma
    0.46
     macrophage
    0.44
     odometer
    0.44
     lip
    0.44
    တ်
    0.43
     monocytes
    0.43
    POSITIVE LOGITS
     Tud
    0.50
    সম্পাদক
    0.48
     தொழில
    0.47
    Manisha
    0.46
    Ná
    0.46
    빽
    0.43
    Puede
    0.42
    ্ড
    0.42
    Dieser
    0.41
     인한
    0.41
    Activations Density 0.000%

    No Known Activations