© 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. 51677
    Prev
    Next
    INDEX
    Explanations

    durable and

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

    listing attributes with 'and' or '&'

    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
    uated
    0.43
    aceted
    0.42
    penas
    0.40
    Colonel
    0.39
    boosting
    0.39
    expanding
    0.39
    ooter
    0.38
    🙁
    0.38
    าะ
    0.38
    กัด
    0.37
    POSITIVE LOGITS
     kuna
    0.45
     joc
    0.43
     Beispiel
    0.42
     şöyle
    0.42
     Xan
    0.41
     slučaj
    0.41
     neće
    0.40
     dwa
    0.39
    ላ
    0.39
     يس
    0.39
    Activations Density 0.000%

    No Known Activations