© 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. 40-GEMMASCOPE-2-RES-262K
    7. 28692
    Prev
    Next
    INDEX
    Explanations

    factual vs subjective

    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_40_width_262k_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
    Realistic
    0.48
    禁用
    0.45
     realistic
    0.44
     sensibly
    0.44
     realistically
    0.44
    甯
    0.42
    经典
    0.41
    outil
    0.40
     निजात
    0.40
    鼍
    0.40
    POSITIVE LOGITS
     subjective
    1.40
     anecdotal
    1.18
     conjecture
    1.13
     subjekt
    1.10
     hearsay
    1.08
     speculation
    1.01
     opinions
    0.99
     conject
    0.96
     subjectivity
    0.96
     inferences
    0.96
    Activations Density 0.018%

    No Known Activations