© 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. 198304
    Prev
    Next
    INDEX
    Explanations

    you, notified, babies, might

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

    phrases with specific subsequent elements

    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
    瘠
    0.49
    netje
    0.47
    mojo
    0.46
    προ
    0.45
    φαν
    0.44
     بالك
    0.43
     రాజ
    0.43
    åk
    0.43
     ਰਾ
    0.43
    ورد
    0.43
    POSITIVE LOGITS
     invites
    0.46
     constante
    0.44
     $<$
    0.43
     supernatural
    0.43
    }.$
    0.43
     situés
    0.43
     HAVING
    0.42
     marche
    0.42
     existentes
    0.42
     aparent
    0.42
    Activations Density 0.000%

    No Known Activations