© 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. 7941
    Prev
    Next
    INDEX
    Explanations

    causes and consequences

    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
    aih
    1.28
    −−
    1.26
    ＇
    1.23
    ・・
    1.22
    ']=$
    1.21
    ─
    1.21
    %}
    1.16
     मंत्रि
    1.12
    =((
    1.11
    }-(
    1.10
    POSITIVE LOGITS
     ~
    2.16
     >
    1.98
     /
    1.80
     ><
    1.79
     =
    1.78
     →
    1.77
     ->
    1.72
     ≠
    1.70
     +
    1.68
     <>
    1.58
    Activations Density 0.364%

    No Known Activations