© 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. 7564
    Prev
    Next
    INDEX
    Explanations

    resolveescalate intoongoing investigationsignificant discount

    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
    Stage
    0.91
     नकार
    0.89
    方位
    0.89
    दिनी
    0.87
    ंचे
    0.86
     Stages
    0.86
    έν
    0.85
    瓴
    0.85
    钎
    0.84
    enz
    0.84
    POSITIVE LOGITS
    riages
    1.04
     Kees
    1.04
     unless
    1.02
    XXXXXXXX
    1.01
     Julia
    0.96
     Marjorie
    0.95
    ૃહ
    0.95
     XXX
    0.94
    POT
    0.94
     nia
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.