© 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. 2307
    Prev
    Next
    INDEX
    Explanations

    possessive followed by noun/adjective

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

    possessive + noun for state or action

    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
     शरीर
    0.22
     jedna
    0.22
     disappears
    0.21
     -\
    0.21
     hormones
    0.21
     patted
    0.21
     れ
    0.20
     contradicts
    0.20
     είναι
    0.20
     jų
    0.20
    POSITIVE LOGITS
     penchant
    0.26
     longstanding
    0.22
    4
    0.22
     realist
    0.21
     zahlreichen
    0.20
     многочис
    0.20
     consultative
    0.20
     cuidado
    0.20
    Er
    0.19
     endeavors
    0.19
    Activations Density 1.065%

    No Known Activations