© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78189
    Prev
    Next
    INDEX
    Explanations

    villainous unsettling things

    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
    欴
    0.49
    おしゃれ
    0.46
    os
    0.46
    ot
    0.46
    お
    0.46
    즈
    0.45
    ι
    0.43
    ala
    0.43
     ঐ
    0.42
    ק
    0.42
    POSITIVE LOGITS
     Destroy
    0.49
     Traff
    0.49
     Decay
    0.48
    Խ
    0.44
     Virus
    0.43
     Simulator
    0.43
     dysfunctional
    0.43
     Maintain
    0.43
     Crystall
    0.43
     Richtung
    0.42
    Activations Density 0.005%

    No Known Activations