© 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. 172646
    Prev
    Next
    INDEX
    Explanations

    words ending or starting with specific letters

    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
    1
    0.15
    8
    0.13
    5
    0.13
    7
    0.12
    Max
    0.12
    K
    0.11
    3
    0.11
    6
    0.11
    9
    0.11
    4
    0.10
    POSITIVE LOGITS
     sillons
    0.15
     ڈھ
    0.13
     كيفية
    0.13
     دریا
    0.12
     lagoons
    0.12
     cavité
    0.12
     கடற்க
    0.12
     مواد
    0.12
    sadpoetry
    0.12
     جلو
    0.12
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.