© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4351
    Prev
    Next
    INDEX
    Explanations

    ui layout and benefits

    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_17_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
     இயக்குநர்
    1.01
    Speech
    0.93
     específicas
    0.93
    茠
    0.89
    Phrase
    0.88
    <unused2160>
    0.87
    됨
    0.87
     específica
    0.87
    沨
    0.87
     específicos
    0.85
    POSITIVE LOGITS
     new
    0.74
     deed
    0.72
    laying
    0.70
     detectors
    0.70
     price
    0.69
     production
    0.68
     द्वारा
    0.68
    ash
    0.68
     electricity
    0.68
     cheap
    0.67
    Activations Density 0.003%

    No Known Activations