© 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. 848
    Prev
    Next
    INDEX
    Explanations

    next item, single item, distinct item

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

    common measure, usual suspects, primary way

    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
     fhe
    0.20
    ।
    0.20
             
    0.19
    )。
    0.17
    :,
    0.17
    ính
    0.17
    ;\
    0.17
         
    0.17
     verschied
    0.17
                             
    0.17
    POSITIVE LOGITS
     accolade
    0.21
     masterpiece
    0.21
     conundrum
    0.20
     foray
    0.20
     loophole
    0.19
     idea
    0.18
     altercation
    0.18
     dilemma
    0.18
     hashtag
    0.18
     predicament
    0.18
    Activations Density 0.868%

    No Known Activations