© 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. 22-GEMMASCOPE-2-RES-16K
    7. 2224
    Prev
    Next
    INDEX
    Explanations

    leaving or returning

    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_22_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
    vius
    0.62
     পারবে
    0.62
    要在
    0.59
     బహి
    0.58
    憎
    0.57
    옛
    0.57
     بلد
    0.56
     گرو
    0.56
    }+(\
    0.54
    ্ল্ড
    0.54
    POSITIVE LOGITS
     leaving
    0.73
     leaves
    0.70
     leave
    0.68
    amethasone
    0.67
     revient
    0.65
    breadcrumb
    0.64
     microglia
    0.64
    oger
    0.63
    leaves
    0.63
    ರಣ
    0.63
    Activations Density 0.170%

    No Known Activations