© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7225
    Prev
    Next
    INDEX
    Explanations

    describing AI capabilities and tasks

    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_22_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
    ⑹
    0.92
     leukaemia
    0.91
     states
    0.89
    чника
    0.86
     здоровье
    0.81
    ా
    0.81
    របស់
    0.81
    кр
    0.80
     čl
    0.80
    苅
    0.80
    POSITIVE LOGITS
     der
    1.32
    adium
    1.26
     Helsing
    1.23
    Der
    1.16
     Gogh
    1.15
    ADIUM
    1.10
     den
    1.09
    ISHING
    1.07
    akkam
    1.07
    ishing
    1.05
    Activations Density 0.033%

    No Known Activations