© 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. 8123
    Prev
    Next
    INDEX
    Explanations

    delve deeper

    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
    稠
    1.04
    ASH
    0.96
     endearing
    0.95
     Shuk
    0.94
     delicate
    0.92
    насти
    0.89
     Schönheit
    0.87
    AKES
    0.86
     delicately
    0.84
     유명
    0.84
    POSITIVE LOGITS
     surveyed
    1.36
     respondents
    1.30
     respondent
    1.22
     polled
    1.09
     (%)
    1.09
     Respondents
    1.04
     survey
    1.02
     entrevist
    0.98
     reported
    0.94
     responden
    0.93
    Activations Density 0.122%

    No Known Activations