© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9735
    Prev
    Next
    INDEX
    Explanations

    State Street Mastercard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     pit
    0.98
    ngày
    0.88
    गु
    0.86
    دع
    0.85
     جز
    0.85
     ח
    0.82
     در
    0.82
    渇
    0.82
    Well
    0.80
     ucz
    0.80
    POSITIVE LOGITS
     score
    1.15
    ceram
    1.13
    score
    1.12
    
    1.11
    ൂരി
    1.11
    
    1.06
    ට්ට
    1.05
    Escolhido
    1.04
    cA
    1.04
    ີ່
    1.03
    Activations Density 0.000%

    No Known Activations