© 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. 32708
    Prev
    Next
    INDEX
    Explanations

    numbers and directions

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

    number seven

    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
     accommodate
    0.50
    뗑
    0.44
     fonctionnalité
    0.43
    乆
    0.43
    ("*
    0.42
     nimi
    0.42
    ствует
    0.42
     reorganize
    0.42
    ोष
    0.41
    (/
    0.41
    POSITIVE LOGITS
    seven
    0.48
     सात
    0.46
    coast
    0.45
    ssel
    0.43
     সাত
    0.43
     семи
    0.43
    rand
    0.42
    cons
    0.42
     జన
    0.42
     on
    0.41
    Activations Density 0.000%

    No Known Activations