© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7767
    Prev
    Next
    INDEX
    Explanations

    digital and virtual applications

    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
    𝐞
    3.18
    𝐟
    2.56
    𝐚
    2.55
    𝐬
    2.53
    𝐥
    2.49
    ೂರ್ವ
    2.49
    𝐫
    2.47
    𝐮
    2.44
    âce
    2.40
    𝐨
    2.37
    POSITIVE LOGITS
    NgModule
    2.00
    oos
    1.98
    ۰
    1.93
    ստ
    1.92
     pozw
    1.89
    HTTPSampler
    1.84
    VERTISEMENT
    1.84
    ially
    1.80
    პირ
    1.80
    LVANIA
    1.77
    Activations Density 0.712%

    No Known Activations