© 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-16K
    7. 1696
    Prev
    Next
    INDEX
    Explanations

    national helpline

    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_16k_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
    ^{+}(
    0.89
     affliction
    0.89
     holocaust
    0.87
     Untersuchung
    0.85
    भारत
    0.84
     ajuta
    0.82
     counselling
    0.82
    ̘
    0.80
     Holocaust
    0.79
     занимается
    0.79
    POSITIVE LOGITS
     direkt
    0.75
    IVIDUAL
    0.68
    直接
    0.68
     directly
    0.68
     direct
    0.65
    すら
    0.63
    кович
    0.63
     all
    0.63
     mobile
    0.62
    all
    0.61
    Activations Density 0.067%

    No Known Activations