© 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. 22-GEMMASCOPE-2-RES-262K
    7. 5278
    Prev
    Next
    INDEX
    Explanations

    financial ruin, relating to, late

    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_22_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
    รู้
    1.20
     gdy
    1.18
    nji
    1.14
    '{
    1.13
    نیم
    1.12
    n
    1.11
    inations
    1.10
    termilk
    1.09
    ک
    1.08
     ejac
    1.06
    POSITIVE LOGITS
    letos
    1.04
    Carlton
    1.02
    ]))
    1.01
    ২০
    1.01
    at
    1.00
    мі
    1.00
    seed
    1.00
    ]),
    0.99
     seeded
    0.96
     unab
    0.95
    Activations Density 0.000%

    No Known Activations