© 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. 249306
    Prev
    Next
    INDEX
    Explanations

    our Catalog

    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
     পল
    0.53
     repel
    0.52
     especie
    0.52
     substantiate
    0.51
     importanti
    0.49
     funktionieren
    0.47
    躹
    0.47
     youre
    0.47
     erleben
    0.47
    রাস
    0.47
    POSITIVE LOGITS
    _{(
    0.47
    л
    0.45
    ութ
    0.43
    もっと
    0.42
    ött
    0.41
     Sdn
    0.40
    Sk
    0.40
    етра
    0.40
     vuoden
    0.40
    ל
    0.40
    Activations Density 0.001%

    No Known Activations