© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 8328
    Prev
    Next
    INDEX
    Explanations

    will followed by verb

    np_acts-logits-general · gemini-2.5-flash-lite

    will not or will strive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     axioms
    0.17
     weiß
    0.17
    })$.
    0.16
    ្ឋ
    0.15
     enzymes
    0.15
    ను
    0.15
    。
    0.15
    ។
    0.15
    unnels
    0.15
    𝔀
    0.15
    POSITIVE LOGITS
     gladly
    0.20
     promote
    0.19
     encourage
    0.18
    積極的に
    0.17
     not
    0.17
     continue
    0.17
     provide
    0.16
     perpetuate
    0.16
     therefore
    0.16
     make
    0.15
    Activations Density 0.784%

    No Known Activations