© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12175
    Prev
    Next
    INDEX
    Explanations

    details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    ಾನ
    0.60
    思想
    0.57
     McCon
    0.55
     केमिक
    0.54
    ऋ
    0.54
     Marcello
    0.54
    薷
    0.54
    ?’”
    0.53
     डिजिटल
    0.52
     Mél
    0.50
    POSITIVE LOGITS
     детали
    0.61
     invading
    0.54
     particulars
    0.51
     objed
    0.51
     namam
    0.50
     deliberate
    0.50
    ствима
    0.49
    --;
    0.49
     detal
    0.49
     details
    0.49
    Activations Density 0.006%

    No Known Activations