© 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. 4419
    Prev
    Next
    INDEX
    Explanations

    transcended, timbre, hoarse

    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
    Duel
    1.38
    铅
    1.38
    ériences
    1.33
    plings
    1.31
    okines
    1.31
     Gord
    1.28
     Geol
    1.26
     Actin
    1.25
    wiches
    1.25
     <%
    1.24
    POSITIVE LOGITS
    直到
    1.11
     debía
    1.10
     seguridad
    0.99
     precisar
    0.98
     vardı
    0.94
    絕對
    0.94
     uważ
    0.91
     frisk
    0.90
    рів
    0.89
    绝对
    0.87
    Activations Density 0.165%

    No Known Activations