© 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. 47877
    Prev
    Next
    INDEX
    Explanations

    the rankings, asked for

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

    android coding (Bundle)

    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
     shipbuilding
    0.43
     XPath
    0.42
     supervision
    0.42
     Wolfram
    0.42
     Ajax
    0.41
     buoyancy
    0.41
     EXC
    0.41
    旧
    0.41
     superconduct
    0.41
    稳定
    0.40
    POSITIVE LOGITS
    innen
    0.50
    zetek
    0.47
    💌
    0.47
    reeting
    0.44
    umiem
    0.44
     Detalles
    0.44
    aufnahme
    0.44
     Ident
    0.44
     nieuws
    0.43
     பர
    0.43
    Activations Density 0.000%

    No Known Activations