© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 137072
    Prev
    Next
    INDEX
    Explanations

    specific collocations and phrases

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

    explaining concepts and examples

    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
    obtenir
    0.51
     ağır
    0.45
    ⇠
    0.44
    ારો
    0.44
    єр
    0.44
    ᕝ
    0.44
     thoracique
    0.43
    íticas
    0.42
    zeppelin
    0.42
    htim
    0.42
    POSITIVE LOGITS
     l
    0.45
     Diary
    0.44
     ב
    0.43
    Logical
    0.42
     Lava
    0.42
    Diary
    0.42
     Bridges
    0.41
    Viva
    0.41
     Logic
    0.41
    Logic
    0.41
    Activations Density 0.000%

    No Known Activations