© 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. 168648
    Prev
    Next
    INDEX
    Explanations

    foreign names and locations

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

    a regular phrase

    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
     привести
    0.47
    том
    0.45
    ífica
    0.45
    ega
    0.45
     нав
    0.44
    JECT
    0.43
     է
    0.43
    ſt
    0.43
    ono
    0.43
    olla
    0.43
    POSITIVE LOGITS
    tenth
    0.48
    더
    0.46
     روست
    0.46
     Petrus
    0.45
    보고
    0.45
     Tatiana
    0.45
     tigris
    0.44
     Hazrat
    0.44
    첩
    0.44
     Sunil
    0.44
    Activations Density 0.000%

    No Known Activations