© 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. 162539
    Prev
    Next
    INDEX
    Explanations

    selected operatingback to back mountingseveral businessextremely rare

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

    Direct sunlight, same Region, five people

    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
    ,
    0.49
     Quin
    0.47
     extremely
    0.47
    Durante
    0.46
    Arabic
    0.45
     Ayat
    0.44
     Dinge
    0.43
    行う
    0.41
    Facts
    0.41
     Jeremiah
    0.41
    POSITIVE LOGITS
    ଟି
    0.56
    𝐳
    0.47
     erstes
    0.45
     န
    0.45
    printf
    0.45
     inhab
    0.45
    adid
    0.45
     rodzin
    0.44
     cuadrados
    0.44
    vere
    0.44
    Activations Density 0.000%

    No Known Activations