© 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. 64065
    Prev
    Next
    INDEX
    Explanations

    phrases and their continuations

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

    shells, zombies, depending on

    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
     hton
    0.50
     impair
    0.47
     longstanding
    0.44
    ^{
    0.43
     دوس
    0.43
     diminishing
    0.43
     }$
    0.43
    ersi
    0.43
     vowels
    0.43
     오랜
    0.41
    POSITIVE LOGITS
     মনি
    0.50
    Flights
    0.49
    Textures
    0.49
    plan
    0.48
    <unused520>
    0.47
    Monitoring
    0.47
    𝙛
    0.47
    <unused972>
    0.47
    <unused975>
    0.46
    planung
    0.46
    Activations Density 0.000%

    No Known Activations