© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14787
    Prev
    Next
    INDEX
    Explanations

    YouTuber, Super Glue, chicken skin, OnlyFans

    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_13_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
     ρ
    1.51
     vast
    1.36
    ルス
    1.35
     γ
    1.28
     horror
    1.26
     news
    1.26
     компа
    1.21
     mood
    1.21
     hint
    1.19
     noise
    1.19
    POSITIVE LOGITS
     Escuela
    1.59
    Administrative
    1.57
     Shroff
    1.56
    }//
    1.52
    administrative
    1.51
    CustomerID
    1.49
    Personnel
    1.48
    btnLogin
    1.48
    Collaboration
    1.47
    //"
    1.45
    Activations Density 0.000%

    No Known Activations