© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137144
    Prev
    Next
    INDEX
    Explanations

    year, fundraising, necessary

    np_acts-logits-general · gemini-2.5-flash-lite

    stack

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Е
    0.55
     ली
    0.48
    С
    0.48
    ahm
    0.48
    Digest
    0.47
    Ко
    0.47
    VERSE
    0.47
    었고
    0.47
    𝙊
    0.47
    Св
    0.47
    POSITIVE LOGITS
     threatening
    0.45
     Kyushu
    0.43
     economically
    0.43
     underprivileged
    0.42
     годом
    0.42
    bumptech
    0.42
     Azerbaijan
    0.41
     amenaza
    0.41
     undermined
    0.41
     बरबाद
    0.41
    Activations Density 0.001%

    No Known Activations