© 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. 137928
    Prev
    Next
    INDEX
    Explanations

    education and professional activities

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

    words before specific verbs/prepositions

    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
    owskiego
    0.54
    </tbody>
    0.54
     nrow
    0.47
     repo
    0.45
     Xi
    0.45
     profile
    0.45
     toothpick
    0.44
     workloads
    0.44
     RAID
    0.44
     urinal
    0.44
    POSITIVE LOGITS
    หรือ
    0.55
    These
    0.52
    和你
    0.50
    ◘
    0.50
     이런
    0.49
    ,:)
    0.47
    栘
    0.47
    inee
    0.47
     These
    0.47
    €“
    0.47
    Activations Density 0.001%

    No Known Activations