© 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. 16428
    Prev
    Next
    INDEX
    Explanations

    know better

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

    kept or retained

    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
    os
    0.46
     зако
    0.46
    es
    0.46
    ie
    0.45
    Ion
    0.45
     প্রথমে
    0.43
    in
    0.43
    瀕
    0.43
    otras
    0.42
    ot
    0.41
    POSITIVE LOGITS
     রঙ্গ
    0.48
    ാള
    0.45
     quarters
    0.44
     나의
    0.42
     dystopian
    0.41
    委员会
    0.40
    ᙱ
    0.40
    ]},
    0.39
    鉄道
    0.39
     sexism
    0.39
    Activations Density 0.000%

    No Known Activations