© 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. 154678
    Prev
    Next
    INDEX
    Explanations

    seasons and holidays

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

    conditions and processes

    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
    及び
    0.50
    ニ
    0.47
    竣工
    0.46
    જી
    0.45
    ганда
    0.44
    ﻑ
    0.44
    識別
    0.44
    cuando
    0.44
    Timing
    0.44
    と同様
    0.44
    POSITIVE LOGITS
     snowman
    0.63
     hiker
    0.51
     컴
    0.50
     reindeer
    0.50
     hikers
    0.47
     ointment
    0.46
     आए
    0.46
     kom
    0.46
     snowy
    0.45
     parcour
    0.45
    Activations Density 0.001%

    No Known Activations