© 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. 7400
    Prev
    Next
    INDEX
    Explanations

    часто, начали, самостоятельно, что

    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
     tzv
    1.90
     tzw
    1.77
     તથા
    1.67
     pues
    1.66
     అనంతరం
    1.62
     odnosno
    1.62
    ឲ
    1.60
     česk
    1.52
     तमाम
    1.49
    tså
    1.48
    POSITIVE LOGITS
     XNUMX
    2.51
     ​​
    1.95
    NUMX
    1.74
     あなた
    1.73
    制造商
    1.65
    令人
    1.63
    应用程序
    1.61
     möglicherweise
    1.57
    하십시오
    1.55
     ™
    1.51
    Activations Density 0.024%

    No Known Activations