© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 164023
    Prev
    Next
    INDEX
    Explanations

    policy, privacy, non

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

    violet nebula, concrete discussions, steam whistles

    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
     offense
    0.47
     as
    0.43
    &
    0.41
     صعب
    0.40
    GoAbroad
    0.40
    Sig
    0.39
    Hoch
    0.39
    Texas
    0.39
     &
    0.39
    gegen
    0.39
    POSITIVE LOGITS
     displayText
    0.47
     golongan
    0.47
     palin
    0.47
     garis
    0.46
    तिर
    0.46
     dones
    0.45
     kelu
    0.45
    ტერ
    0.45
     sommeil
    0.45
     glfw
    0.45
    Activations Density 0.000%

    No Known Activations