© 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. 73519
    Prev
    Next
    INDEX
    Explanations

    predicting 'will'

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

    viral video titles, anonymous users, follow-up after, internal reasons, customer name

    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
     Didn
    0.52
    कब
    0.50
     didn
    0.48
     fehlen
    0.48
    riech
    0.47
     Wasn
    0.46
     휴
    0.46
     ول
    0.46
     Nagy
    0.45
     lokal
    0.45
    POSITIVE LOGITS
    あなた
    0.49
    আপনি
    0.47
    あなたは
    0.47
    хоро
    0.46
     NASDAQ
    0.46
    increment
    0.44
     increment
    0.44
     Increment
    0.44
     Incre
    0.43
     можете
    0.43
    Activations Density 0.006%

    No Known Activations