© 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
    2. Gemma-3-270M
    3. 15-GEMMASCOPE-2-RES-16K
    4. 2133
    Prev
    Next
    INDEX
    Explanations

    strategy and planning

    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
    }]\
    1.64
    }]
    1.50
    }]{
    1.48
    .}\
    1.44
    ]==
    1.42
    】【
    1.41
    ]!=
    1.35
    }],
    1.33
    )}]
    1.32
    ]];
    1.32
    POSITIVE LOGITS
    contract
    1.01
    berts
    0.98
    傭
    0.96
     Contract
    0.94
    mpa
    0.94
    bid
    0.94
    promise
    0.93
    ald
    0.92
     garant
    0.92
    icky
    0.91
    Activations Density 0.028%

    No Known Activations