© 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. 13680
    Prev
    Next
    INDEX
    Explanations

    user hi followed by punctuation

    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
     (%
    1.22
    탤
    1.19
     '*
    1.11
    󰀄
    1.08
     APT
    1.08
     Или
    1.07
    proba
    1.07
     (§
    1.06
    SegmentInfo
    1.05
     %%
    1.05
    POSITIVE LOGITS
    mlung
    1.02
    God
    1.00
     ricerche
    0.99
     presto
    0.98
     um
    0.97
     trovato
    0.96
     cambiato
    0.95
    শির
    0.95
    发现
    0.95
    حد
    0.94
    Activations Density 0.108%

    No Known Activations