© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11351
    Prev
    Next
    INDEX
    Explanations

    take on new roles

    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_7_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
    긋
    2.23
     Correlation
    2.21
    ্কর
    2.17
     Want
    2.16
    なわ
    2.10
    اٹ
    1.96
     Making
    1.96
     Let
    1.95
     Staying
    1.95
     Bring
    1.94
    POSITIVE LOGITS
    얼
    2.57
    रोवर
    2.32
    忑
    2.31
    गड
    2.23
    
    2.23
    ói
    2.18
    راحی
    2.17
    reo
    2.16
    𝐠
    2.11
     shadows
    2.10
    Activations Density 0.035%

    No Known Activations