© 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. 57733
    Prev
    Next
    INDEX
    Explanations

    special occasion languages Africa

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

    film, Web, produce, him

    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
    ."
    0.52
    ires
    0.48
    re
    0.45
    .")
    0.45
    ,"
    0.44
    mel
    0.44
    .]
    0.44
    ee
    0.43
    .}
    0.43
    ]
    0.42
    POSITIVE LOGITS
     признаки
    0.59
     maquillaje
    0.53
     procedimento
    0.49
     bicarbon
    0.48
     myArray
    0.48
     Texture
    0.48
     procedimiento
    0.48
    ভৌম
    0.48
     peptid
    0.47
     filme
    0.47
    Activations Density 0.000%

    No Known Activations