© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 2147
    Prev
    Next
    INDEX
    Explanations

    creating a new item

    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
    iensis
    2.45
    براير
    2.28
    eing
    2.11
    ಾ
    2.10
     senjata
    2.07
     Es
    2.05
    ৌশ
    2.04
    ei
    2.03
     Ese
    2.02
    驒
    2.01
    POSITIVE LOGITS
    orent
    2.10
    toFixed
    2.03
    ANS
    2.00
    ৬০
    1.92
    vy
    1.78
    Sal
    1.77
    Crystal
    1.70
    sal
    1.69
    PluginResult
    1.69
    renal
    1.69
    Activations Density 1.422%

    No Known Activations