© 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. 218974
    Prev
    Next
    INDEX
    Explanations

    sequences followed by nouns/verbs

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

    word antonym pairs and definitions

    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
    اند
    0.51
    PRE
    0.51
     phủ
    0.50
    悩
    0.49
    ى
    0.46
    نو
    0.45
    ák
    0.45
     potre
    0.45
    كنولوجيا
    0.45
     Disbursements
    0.44
    POSITIVE LOGITS
     περίπτωση
    0.53
     fasten
    0.47
     limb
    0.47
    ໋
    0.45
    ńskich
    0.44
     DbSet
    0.41
    ского
    0.41
    פט
    0.41
     Borges
    0.41
     limbs
    0.40
    Activations Density 0.000%

    No Known Activations