© 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-16K
    7. 1245
    Prev
    Next
    INDEX
    Explanations

    National Helpline or Bomb

    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_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
     utils
    1.35
     fashioned
    1.24
     rass
    1.23
     unwell
    1.23
    这
    1.22
    etted
    1.21
     heels
    1.21
     علت
    1.20
     workings
    1.20
     mounts
    1.18
    POSITIVE LOGITS
    CEM
    1.34
    ir
    1.34
    n
    1.31
     വ്യക്ത
    1.29
    emission
    1.29
    un
    1.27
    G
    1.25
    тет
    1.24
    א
    1.23
    Accelerator
    1.23
    Activations Density 0.364%

    No Known Activations