© 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. 187905
    Prev
    Next
    INDEX
    Explanations

    yet crucial

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

    project descriptions

    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
     god
    0.46
    ')
    0.44
    謀
    0.43
     hogi
    0.43
    ']
    0.43
     bū
    0.42
     ゲーム
    0.42
     sumptuous
    0.42
     furnish
    0.42
    つける
    0.42
    POSITIVE LOGITS
    无效
    0.47
     ASSEMBLY
    0.46
    ية
    0.46
    㧋
    0.45
    橑
    0.43
    كار
    0.43
    顽
    0.43
    مركز
    0.42
    到的
    0.41
    接下来
    0.41
    Activations Density 0.000%

    No Known Activations