© 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. 2727
    Prev
    Next
    INDEX
    Explanations

    customer experience and systems

    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
    .).
    2.48
    .].
    2.46
     }).
    2.40
    ]).
    2.40
    .)).
    2.36
    })$.
    2.32
     }.
    2.31
    )).
    2.20
     ].
    2.19
     :).
    2.17
    POSITIVE LOGITS
     eagerly
    1.18
     popularly
    1.17
     suddenly
    1.15
     underwent
    1.15
     abruptly
    1.12
     gracefully
    1.05
     received
    1.04
     enjoyed
    1.02
     celebrated
    1.01
     eserc
    1.01
    Activations Density 0.211%

    No Known Activations