© 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. 53061
    Prev
    Next
    INDEX
    Explanations

    sentiment analysis

    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
    Philosophy
    0.45
    Brain
    0.45
    Lessons
    0.44
     электри
    0.43
     изда
    0.40
    Storyboard
    0.40
    栻
    0.39
    Photography
    0.39
    㗊
    0.39
    Committee
    0.39
    POSITIVE LOGITS
     mentions
    0.74
     sentiment
    0.71
     tweets
    0.69
     NLP
    0.67
     textual
    0.66
     Sentiment
    0.66
    tweets
    0.66
     nltk
    0.65
     texts
    0.63
     corpus
    0.63
    Activations Density 0.401%

    No Known Activations