© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 17-GEMMASCOPE-2-RES-16K
    7. 1390
    Prev
    Next
    INDEX
    Explanations

    respectively and list items

    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_17_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
    facilit
    1.13
    along
    1.05
    gespr
    1.05
    ialog
    1.02
    bation
    0.99
    promoting
    0.98
    accompanied
    0.97
    ὃ
    0.95
    specifically
    0.95
    ULATION
    0.94
    POSITIVE LOGITS
     എന്നീ
    1.65
     등의
    1.64
    等地
    1.64
     등을
    1.57
    etc
    1.55
     എന്നിവ
    1.54
    などを
    1.53
     etc
    1.53
     എന്നി
    1.51
     각각
    1.49
    Activations Density 0.501%

    No Known Activations