© 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. 8115
    Prev
    Next
    INDEX
    Explanations

    actions and descriptions

    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
    𝙉
    1.87
     BadRequest
    1.84
    ཛ
    1.80
    狩
    1.79
    ರ್ಶ
    1.77
    ELIST
    1.77
    榷
    1.74
     मो
    1.74
    枓
    1.72
     каза
    1.72
    POSITIVE LOGITS
    sleep
    1.80
    ly
    1.56
    கன்
    1.55
    home
    1.47
    small
    1.44
    son
    1.41
    le
    1.41
    base
    1.40
    time
    1.39
    bole
    1.38
    Activations Density 0.000%

    No Known Activations