© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5482
    Prev
    Next
    INDEX
    Explanations

    Guardian, Lancet, Conversation, angular

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    ោធ
    2.10
    rifice
    2.04
    𝐡
    2.01
    तरीय
    2.00
    یشہ
    2.00
    ancellor
    1.99
    اج
    1.91
    ৃহে
    1.88
    ্যন্ত
    1.87
    اپ
    1.86
    POSITIVE LOGITS
    čin
    2.09
    ()}')
    2.08
    unsch
    2.01
     MongoClient
    1.97
    čina
    1.95
     wyra
    1.92
    </h4>
    1.92
    idemargin
    1.88
    худ
    1.81
    +}\
    1.81
    Activations Density 0.429%

    No Known Activations