© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 4398
    Prev
    Next
    INDEX
    Explanations

    multi-word completions

    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_12_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
    pportun
    1.45
    姆
    1.20
     قیم
    1.12
     emas
    0.97
     decorate
    0.96
     opportunity
    0.94
     contemporaries
    0.92
    pportunities
    0.91
    猎
    0.89
     opportunità
    0.89
    POSITIVE LOGITS
    stantially
    2.65
    ствах
    2.58
    screw
    2.48
     }}}
    2.44
    性の
    2.41
    nesdays
    2.40
     wabarakatuh
    2.38
    員の
    2.37
    eways
    2.37
    ListOf
    2.36
    Activations Density 0.010%

    No Known Activations