© 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. 11764
    Prev
    Next
    INDEX
    Explanations

    concerns and critiques

    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
     spacious
    1.30
    ↵
    1.10
    Get
    1.09
    素敵な
    1.08
     get
    1.03
     =
    1.00
     good
    1.00
     +
    0.99
     delicious
    0.99
     beautiful
    0.99
    POSITIVE LOGITS
     criticised
    1.76
     criticized
    1.67
     spearheaded
    1.65
     dirigentes
    1.64
     geopolitical
    1.63
     discredited
    1.61
     objected
    1.58
     untenable
    1.52
     breached
    1.47
     exacerbated
    1.47
    Activations Density 0.039%

    No Known Activations