© 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. 36180
    Prev
    Next
    INDEX
    Explanations

    relative pronoun, object keys, feel cold

    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
    ertos
    0.43
     ఐ
    0.42
    elling
    0.41
    ahl
    0.40
    erton
    0.39
     markings
    0.39
    agl
    0.38
     statement
    0.38
     Созда
    0.38
    athl
    0.38
    POSITIVE LOGITS
     indispensables
    0.50
     temporadas
    0.47
     indispens
    0.46
     trabalho
    0.45
    便
    0.45
    騾
    0.45
     garantizar
    0.44
     entreten
    0.43
     sahaja
    0.43
     jejich
    0.43
    Activations Density 0.014%

    No Known Activations