© 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. 17-GEMMASCOPE-2-RES-16K
    7. 12519
    Prev
    Next
    INDEX
    Explanations

    detectron2 Rapid7 dwdm vbetool

    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_17_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
    and
    0.66
    atever
    0.65
    f
    0.63
    astly
    0.56
    g
    0.54
    هرب
    0.53
    j
    0.53
    ський
    0.53
    ancienne
    0.52
    x
    0.52
    POSITIVE LOGITS
     rigorous
    0.52
     cusp
    0.49
     diligent
    0.48
     gloss
    0.48
     logistical
    0.48
     thoughtful
    0.48
     courteous
    0.47
     longstanding
    0.47
     tuple
    0.47
     popcorn
    0.47
    Activations Density 0.040%

    No Known Activations