© 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. 1236
    Prev
    Next
    INDEX
    Explanations

    street, sci-fi, summer, style, fiction

    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
    ity
    2.05
    sided
    2.01
     actu
    1.99
    ים
    1.91
    eso
    1.89
    ก
    1.87
    ших
    1.86
    ми
    1.84
    sheet
    1.82
     official
    1.76
    POSITIVE LOGITS
     rubbing
    2.11
     vibes
    1.97
    蝟
    1.96
     nightmare
    1.92
     bitch
    1.90
     nghiệm
    1.88
    雳
    1.88
     neutroph
    1.88
     كله
    1.87
    Რ
    1.86
    Activations Density 0.283%

    No Known Activations