© 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-262K
    7. 11673
    Prev
    Next
    INDEX
    Explanations

    text-to-image

    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_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
    م
    1.28
    ва
    1.23
    ই
    1.13
    ル
    1.11
     hundred
    1.10
    ᴏ
    1.03
    ustellen
    1.00
     стен
    1.00
     چه
    0.99
    ো
    0.98
    POSITIVE LOGITS
    jenigen
    1.52
     exorbit
    1.32
    otur
    1.26
    claves
    1.24
     modalités
    1.23
    rakech
    1.23
     trovato
    1.21
    ále
    1.21
     unzip
    1.21
     fixé
    1.21
    Activations Density 0.000%

    No Known Activations