© 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
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 3509
    Prev
    Next
    INDEX
    Explanations

    JSON structure closing characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
     cięż
    1.83
     encant
    1.68
     tumb
    1.66
     publiée
    1.60
     nazy
    1.57
     bookmark
    1.56
     nadzie
    1.56
    乜
    1.52
    肿
    1.50
     پشتی
    1.49
    POSITIVE LOGITS
    >),
    1.69
    }],
    1.68
    )}$,
    1.55
    }]$,
    1.55
    »),
    1.48
    }}$,
    1.44
    )},
    1.44
    },}
    1.42
    )],
    1.40
    })$,
    1.37
    Activations Density 0.053%

    No Known Activations