© 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-16K
    7. 13507
    Prev
    Next
    INDEX
    Explanations

    emotions and concepts

    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_16k_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
     is
    0.51
     on
    0.45
     was
    0.44
     of
    0.44
    I
    0.43
    ↵↵
    0.43
    1
    0.42
    _
    0.41
     in
    0.40
    4
    0.40
    POSITIVE LOGITS
    恐惧
    0.39
    ableConcept
    0.37
     인식
    0.37
    𒁁
    0.36
    Benzoimidazol
    0.36
    Begriff
    0.36
     filoz
    0.35
    DataXYZ
    0.35
    煸
    0.35
    崤
    0.35
    Activations Density 0.001%

    No Known Activations