© 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. 138255
    Prev
    Next
    INDEX
    Explanations

    personalised custom design

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

    He quietly, I access, tried to

    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
    舞台
    0.51
    日內
    0.50
    煸
    0.49
    이블
    0.48
    洵
    0.46
    𝖽
    0.46
    不良
    0.46
    泸
    0.46
     Nxe
    0.46
    要是
    0.46
    POSITIVE LOGITS
     excepciones
    0.46
    Approx
    0.46
    ประมาณ
    0.45
    chia
    0.45
    otropin
    0.45
     ประมาณ
    0.44
     πολυ
    0.44
    ci
    0.44
     conductas
    0.44
    Orth
    0.43
    Activations Density 0.001%

    No Known Activations