© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75424
    Prev
    Next
    INDEX
    Explanations

    "personal use", "driver relies", "reversed if"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    かつ
    0.44
    ファイ
    0.43
    マイクロ
    0.42
    𝑄
    0.42
    ワイ
    0.41
    <0x18>
    0.41
    ペース
    0.41
    FEB
    0.40
    ак
    0.40
    길
    0.39
    POSITIVE LOGITS
     waterfowl
    0.51
     Energie
    0.48
     पाण्याची
    0.48
    Ary
    0.46
     ಕಾರ್ಯ
    0.43
     Reputation
    0.43
     untold
    0.42
     water
    0.41
     Battery
    0.41
    ConfigSource
    0.41
    Activations Density 0.005%

    No Known Activations