© 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. 56532
    Prev
    Next
    INDEX
    Explanations

    without this

    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
    ↵
    0.50
    ق
    0.48
     numbers
    0.44
     methods
    0.43
    ла
    0.42
     coursework
    0.41
    q
    0.40
     does
    0.40
    food
    0.40
     general
    0.40
    POSITIVE LOGITS
     Cádiz
    0.48
    💧
    0.47
    usstsein
    0.46
    णसी
    0.45
    humidité
    0.45
    猞
    0.43
    어도
    0.43
     voda
    0.43
     взаимодей
    0.42
     getWeather
    0.42
    Activations Density 0.016%

    No Known Activations