© 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. 3599
    Prev
    Next
    INDEX
    Explanations

    telling Reuters about phasing out technology

    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
    İK
    1.78
     چڑھ
    1.55
     রো
    1.44
    tie
    1.44
    SL
    1.43
    缚
    1.40
    SIG
    1.38
    ন্ব
    1.35
    弯
    1.35
    防
    1.35
    POSITIVE LOGITS
     Late
    1.72
     giai
    1.72
     overlap
    1.67
    การณ์
    1.66
     Iyer
    1.65
     Keenan
    1.64
     situa
    1.63
     Callable
    1.62
     rearrangements
    1.62
     antérieurs
    1.59
    Activations Density 0.000%

    No Known Activations