© 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. 245489
    Prev
    Next
    INDEX
    Explanations

    technical or communication terms

    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
    marine
    0.54
    sink
    0.48
    hills
    0.48
    encoded
    0.45
    yield
    0.45
    ineries
    0.45
    distributed
    0.44
    с
    0.43
    inn
    0.42
    scenes
    0.41
    POSITIVE LOGITS
    חת
    0.58
    隴
    0.48
    ্ল
    0.46
     importing
    0.46
    쨩
    0.46
     importe
    0.46
     सगळे
    0.46
    总
    0.45
    Dentro
    0.45
    憚
    0.45
    Activations Density 0.001%

    No Known Activations