© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10983
    Prev
    Next
    INDEX
    Explanations

    Poe account blocked

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    €™
    2.49
    
    2.47
    dagen
    2.30
    
    2.30
     hev
    2.25
    c
    2.25
     sienta
    2.22
    是
    2.21
    ও
    2.18
    Biggest
    2.18
    POSITIVE LOGITS
    り
    2.29
    項
    2.11
    ,]
    2.11
    ]},
    2.08
    вна
    2.07
    사항
    2.06
     дополнительных
    2.05
    Ꮙ
    2.03
     слов
    2.03
    вів
    2.03
    Activations Density 0.002%

    No Known Activations