© 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. 2150
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    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
     solubility
    1.28
    iseconds
    1.19
    តិ
    1.16
    staben
    1.15
     paraphrase
    1.13
    📎
    1.12
    また
    1.10
     inadequate
    1.10
    ности
    1.10
     reasonableness
    1.08
    POSITIVE LOGITS
    ל
    1.15
     protagonista
    1.11
    ია
    1.11
     protagonisti
    1.11
    +
    1.10
    х
    1.10
    on
    1.09
     hinn
    1.07
    я
    1.03
    Est
    0.99
    Activations Density 0.530%

    No Known Activations