© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3300
    Prev
    Next
    INDEX
    Explanations

    closing </style> tag

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    2.07
    ,
    2.01
    for
    2.01
    and
    1.99
    3
    1.94
    1
    1.88
    9
    1.86
    ’
    1.85
    5
    1.81
    of
    1.81
    POSITIVE LOGITS
     Zusatz
    2.15
     lineColorSpace
    2.06
     Gewer
    2.03
     useNavigate
    2.02
    setKeepCallback
    2.01
    𒁾
    1.99
    퍁
    1.98
    𒆨
    1.96
    טאטורק
    1.96
    𒀊
    1.95
    Activations Density 0.082%

    No Known Activations