© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23861
    Prev
    Next
    INDEX
    Explanations

    equivalent concepts across languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ®.
    0.58
    ։
    0.57
    *.
    0.53
    ).}
    0.52
    ).
    0.51
     매우
    0.50
    ™.
    0.50
    ()}.
    0.50
    .。
    0.49
    °.
    0.49
    POSITIVE LOGITS
     magari
    0.47
     is
    0.46
     oneself
    0.43
    哪怕
    0.42
    这么多
    0.38
    するのは
    0.37
     είναι
    0.37
    るのは
    0.36
    したのは
    0.36
     یہاں
    0.35
    Activations Density 0.128%

    No Known Activations