© 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. 219526
    Prev
    Next
    INDEX
    Explanations

    link tothe sentencetheir financesa therapythe brainServer

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

    weight and data size units

    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
     немного
    0.51
    ující
    0.49
     trochu
    0.46
     impressão
    0.46
    elier
    0.45
     גם
    0.45
    recall
    0.45
    つ
    0.45
    ír
    0.45
     좀
    0.45
    POSITIVE LOGITS
     biodegradation
    0.50
     acute
    0.44
    সোমবার
    0.44
     obtaining
    0.43
    ယ
    0.43
     hydration
    0.43
     amine
    0.42
     remedial
    0.42
     stanu
    0.42
     recyclable
    0.41
    Activations Density 0.000%

    No Known Activations