© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 56065
    Prev
    Next
    INDEX
    Explanations

    "attention" and "homosexuality"

    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_65k_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
    हमने
    0.43
     করিলেন
    0.42
     relative
    0.40
    relative
    0.38
     pust
    0.38
     indelible
    0.38
    voie
    0.37
    {~
    0.37
    饰演
    0.36
     cu
    0.36
    POSITIVE LOGITS
    9
    0.44
    禽
    0.44
    㑒
    0.44
    メタル
    0.43
     좋을
    0.43
    蜴
    0.43
    ITY
    0.42
    성에
    0.41
     ২০১২
    0.41
     тури
    0.40
    Activations Density 0.002%

    No Known Activations