© 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. 1613
    Prev
    Next
    INDEX
    Explanations

    the font, path, applicable, numerator, disk, length

    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
     lemb
    1.53
    AppContext
    1.45
     syarat
    1.43
     suyo
    1.33
     silam
    1.32
    હ
    1.32
     menurun
    1.28
     Nói
    1.25
     ladr
    1.24
    ရှား
    1.23
    POSITIVE LOGITS
     파
    1.53
     Α
    1.49
     채
    1.43
     أس
    1.41
     디
    1.40
    eer
    1.40
     а
    1.38
     ✅
    1.37
     LOFT
    1.36
     whose
    1.36
    Activations Density 0.591%

    No Known Activations