© 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. 141837
    Prev
    Next
    INDEX
    Explanations

    mobile technology, blockchain, future, offers, expensive, story, will

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

    tendency for, PS 3

    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
    پیش
    0.47
    ње
    0.47
    藩
    0.47
     Cualquier
    0.46
     qualsiasi
    0.45
     거예요
    0.45
    県
    0.44
    県の
    0.44
    ന്ത്യ
    0.44
    কাঠ
    0.43
    POSITIVE LOGITS
    IER
    0.49
    蟾
    0.48
     গণ্য
    0.47
    ToJson
    0.46
     wip
    0.45
    t
    0.44
     PRIM
    0.43
     ks
    0.43
    Hughes
    0.43
    HAR
    0.43
    Activations Density 0.001%

    No Known Activations