© 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. 29-GEMMASCOPE-2-RES-65K
    7. 3212
    Prev
    Next
    INDEX
    Explanations

    block start after parenthesis

    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_29_width_65k_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
    ={"
    0.86
     keeps
    0.83
    keeps
    0.81
     looks
    0.81
    looks
    0.80
    feels
    0.80
    missione
    0.79
     eases
    0.77
     engages
    0.76
    водит
    0.75
    POSITIVE LOGITS
     continue
    1.04
    continue
    0.86
     return
    0.77
     ((
    0.77
     ++
    0.75
     Continue
    0.74
     glTexCoord
    0.72
     goto
    0.71
     UIApplication
    0.70
    ResumeLayout
    0.69
    Activations Density 0.096%

    No Known Activations