© 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. 16095
    Prev
    Next
    INDEX
    Explanations

    distribution and spread

    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
    ার্ড
    1.95
     gain
    1.81
    ارا
    1.81
     Question
    1.80
    FO
    1.76
    
    1.73
    ्तिक
    1.68
    </table>
    1.66
    ॉन्स
    1.66
     همراه
    1.63
    POSITIVE LOGITS
     равномер
    2.28
    athermy
    2.24
    iciona
    2.10
    DownLatch
    2.09
    gewood
    2.09
    gwood
    2.06
    v
    2.05
     isLoggedIn
    2.04
    ierenden
    2.03
    см
    2.02
    Activations Density 0.251%

    No Known Activations