© 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. 12378
    Prev
    Next
    INDEX
    Explanations

    what it is

    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
     …
    2.09
     leiden
    2.01
    께
    1.93
    ா
    1.86
     ….
    1.85
    ff
    1.85
    izon
    1.83
    ’)
    1.80
     remo
    1.77
     st
    1.77
    POSITIVE LOGITS
     имущества
    2.48
    ícios
    2.40
    脱
    2.38
    桎
    2.31
    轫
    2.27
    踱
    2.23
    guardo
    2.19
     "¿
    2.19
    Ça
    2.18
    玩笑
    2.18
    Activations Density 0.134%

    No Known Activations