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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8762
    Prev
    Next
    INDEX
    Explanations

    possessive abstract nouns

    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
    hadoop
    0.40
    ∀
    0.35
    ╯
    0.34
    真正的
    0.33
    І
    0.33
    ទ្
    0.32
    第九
    0.32
    防
    0.32
    第六
    0.32
    VAR
    0.31
    POSITIVE LOGITS
     agitation
    0.46
     secrecy
    0.46
     exuber
    0.45
     acidity
    0.45
     femininity
    0.43
     lightness
    0.42
     shortness
    0.42
    tense
    0.42
     negativity
    0.42
     materialism
    0.42
    Activations Density 0.050%

    No Known Activations