© 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. 210048
    Prev
    Next
    INDEX
    Explanations

    names of people and things

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

    basic needs

    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
     श्रे
    0.56
    콧
    0.51
    範圍
    0.50
     couches
    0.50
    洧
    0.49
     Стаўкі
    0.49
    즘
    0.49
    ﹁
    0.49
    nPort
    0.48
    넴
    0.48
    POSITIVE LOGITS
     ]
    0.65
    ]
    0.56
     )
    0.55
    j
    0.54
    0.53
     خال
    0.53
    )
    0.52
    -
    0.51
     incest
    0.51
     ,
    0.50
    Activations Density 0.000%

    No Known Activations