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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 12699
    Prev
    Next
    INDEX
    Explanations

    filtering out distractions

    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
     expresar
    0.42
     emoción
    0.42
     emoc
    0.42
     indicaciones
    0.42
     Emotions
    0.41
    㬶
    0.41
     emociones
    0.40
    Ethics
    0.40
     Emotion
    0.40
     ensinar
    0.40
    POSITIVE LOGITS
     lazy
    0.45
     filters
    0.45
     reconstruction
    0.43
     defaults
    0.42
     окон
    0.42
     biases
    0.42
     pool
    0.41
     ignore
    0.41
    門
    0.41
     filter
    0.41
    Activations Density 0.077%

    No Known Activations