© 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. 11117
    Prev
    Next
    INDEX
    Explanations

    Tractors, RTX, salary, corporations, rocket, import

    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
    ங்கிணை
    1.06
    ੋ
    0.99
    जनबी
    0.88
    Hound
    0.86
    
    0.86
    ئین
    0.84
    udit
    0.83
    }$,
    0.82
     $€
    0.81
    ('#
    0.81
    POSITIVE LOGITS
    ות
    1.08
    ための
    1.02
    uose
    1.02
    f
    0.98
    cknowled
    0.94
    p
    0.91
    yards
    0.88
    ために
    0.87
    sı
    0.87
    mila
    0.87
    Activations Density 0.307%

    No Known Activations