© 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. 14258
    Prev
    Next
    INDEX
    Explanations

    Gemma, model

    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
     кому
    1.30
    threatening
    1.28
     comrades
    1.26
     Pyongyang
    1.24
     خو
    1.24
     labourers
    1.22
     condolences
    1.21
    媾
    1.20
    aneously
    1.19
    casualties
    1.19
    POSITIVE LOGITS
     developer
    0.95
     fil
    0.87
     Bob
    0.85
     Developer
    0.84
    Bob
    0.83
     regler
    0.81
     pro
    0.80
    ores
    0.80
     Scrib
    0.80
     Dee
    0.80
    Activations Density 0.124%

    No Known Activations