© 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. 32090
    Prev
    Next
    INDEX
    Explanations

    this case

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

    maximum height, optimal absorption

    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
     روم
    0.46
    ్రీన్
    0.45
    钚
    0.44
     রাজনীতিবিদ
    0.44
    节点的
    0.44
     ഹിന്ദ
    0.43
    پلز
    0.43
    为此
    0.42
     macron
    0.41
    ຈັດສົ່ງ
    0.41
    POSITIVE LOGITS
    ना
    0.60
     morreu
    0.49
     kesempatan
    0.49
    ने
    0.48
     рассказывает
    0.48
     },
    0.47
     semasa
    0.47
     bhuv
    0.46
    場で
    0.46
    imą
    0.46
    Activations Density 0.000%

    No Known Activations