© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 7792
    Prev
    Next
    INDEX
    Explanations

    Fibonacci sequence definition

    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_12_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
    vér
    1.24
     gång
    1.23
     Bür
    1.20
     Dekker
    1.19
    ohan
    1.15
     settlement
    1.15
    끼
    1.14
     Settlement
    1.14
    setzungen
    1.13
     Versicherung
    1.13
    POSITIVE LOGITS
     تريد
    1.67
    foreground
    1.55
    罕
    1.55
    careers
    1.55
     tahu
    1.47
    colas
    1.46
    activer
    1.45
    forbidden
    1.42
    required
    1.42
    ámicas
    1.42
    Activations Density 0.000%

    No Known Activations