© 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. 151948
    Prev
    Next
    INDEX
    Explanations

    state, rights, positions, hosting, learn

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

    while thinking or fantasizing

    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
    اس
    0.51
    otor
    0.46
    زن
    0.46
    و
    0.45
    دوس
    0.45
    多く
    0.45
     kinship
    0.45
    持ち
    0.44
    ور
    0.44
     معلوم
    0.43
    POSITIVE LOGITS
     आवेश
    0.50
    𝙖
    0.49
    ཎ
    0.48
     अमेरिका
    0.47
     лицен
    0.47
     bukanlah
    0.47
     সৃ
    0.45
     việc
    0.45
     পারেনি
    0.45
     পেরে
    0.45
    Activations Density 0.000%

    No Known Activations