© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4393
    Prev
    Next
    INDEX
    Explanations

    disadvantages following "Dis"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
     škole
    1.02
     saisons
    0.88
    ₂)
    0.84
    ahun
    0.82
     saison
    0.81
     seasons
    0.80
    season
    0.79
    ớp
    0.78
     secondaire
    0.78
     시즌
    0.76
    POSITIVE LOGITS
    █
    1.61
     nanotubes
    1.50
     writer
    1.46
     libel
    1.45
     slander
    1.44
     Wikiped
    1.44
     lobbyists
    1.43
     cyanide
    1.43
     Manuscripts
    1.42
     signatories
    1.41
    Activations Density 0.136%

    No Known Activations