© 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. 143527
    Prev
    Next
    INDEX
    Explanations

    circuit (LT)

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

    illegal or restrictions

    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
    ák
    0.51
     Knights
    0.49
    zám
    0.48
     §
    0.48
     označ
    0.46
     Knight
    0.45
    缉
    0.45
     рад
    0.45
    ukk
    0.44
     equate
    0.43
    POSITIVE LOGITS
    اء
    0.47
    μα
    0.46
    ドア
    0.46
    衣服
    0.46
    ۱۹
    0.45
     indywidual
    0.44
    ло
    0.44
    ⎝
    0.43
    疯狂
    0.43
    ة
    0.42
    Activations Density 0.000%

    No Known Activations