© 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. 1410
    Prev
    Next
    INDEX
    Explanations

    providing help and answers

    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
     compter
    1.57
     verso
    1.55
     Manifest
    1.50
    deload
    1.49
     reprogramming
    1.48
    攣
    1.46
    ilipp
    1.45
     Nantes
    1.41
     horarios
    1.40
    挛
    1.39
    POSITIVE LOGITS
     approfond
    1.19
     enriqu
    1.09
     meaningfully
    0.98
    URIS
    0.96
    راجع
    0.93
    Comments
    0.92
     substant
    0.92
    全文
    0.91
     답변
    0.91
     asesor
    0.89
    Activations Density 0.628%

    No Known Activations