© 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. 11611
    Prev
    Next
    INDEX
    Explanations

    yet not done

    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
     y
    2.34
     pr
    2.34
    un
    2.28
     Ins
    2.25
     LO
    2.24
     CL
    2.18
    엔
    2.11
    _.
    2.11
     Car
    2.07
    Car
    2.05
    POSITIVE LOGITS
    𝒕
    3.72
    𝒊
    3.41
    𝒈
    3.32
    𝒆
    3.09
    𝓇
    3.01
    𝒔
    2.98
    𝒓
    2.96
    𝒅
    2.93
    𝘁
    2.87
    𝒐
    2.86
    Activations Density 0.004%

    No Known Activations