© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 220914
    Prev
    Next
    INDEX
    Explanations

    bundled with other

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

    developed and maintained, core, key

    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
    Negative Logits
    stays
    0.61
    לט
    0.49
    ጳ
    0.49
    俄罗斯
    0.48
    author
    0.46
    òria
    0.46
    은
    0.45
     malay
    0.45
    Workout
    0.43
     eloquence
    0.43
    POSITIVE LOGITS
     equivalently
    0.45
    ingen
    0.42
     VOLUME
    0.42
     hoger
    0.42
     ]),
    0.41
    ového
    0.40
    ovanie
    0.40
    ifed
    0.40
     volumen
    0.39
     Faktor
    0.39
    Activations Density 0.000%

    No Known Activations