© 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. 224615
    Prev
    Next
    INDEX
    Explanations

    ladders, individual, history, earliest, picked, thanks

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

    data definition and naming

    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
    Econom
    0.48
    se
    0.47
    Carolina
    0.47
    as
    0.46
    a
    0.46
    p
    0.45
    стер
    0.45
    an
    0.44
    towards
    0.44
    s
    0.44
    POSITIVE LOGITS
    )
    0.55
     Manifest
    0.52
    ]
    0.52
     മൂ
    0.51
    >
    0.48
     Съ
    0.47
     manifests
    0.47
     Фе
    0.47
     purifying
    0.46
    的意思
    0.45
    Activations Density 0.000%

    No Known Activations