© 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. 7828
    Prev
    Next
    INDEX
    Explanations

    Earth

    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
    IVI
    1.19
     ISC
    1.13
     Knud
    1.03
     출
    1.02
    출
    0.92
    DES
    0.91
    IMP
    0.89
    <0xB4>
    0.88
     presup
    0.88
    JW
    0.86
    POSITIVE LOGITS
     Earth
    3.25
    Earth
    3.05
    earth
    3.02
     earth
    3.02
     earths
    2.92
     EARTH
    2.85
     Erde
    2.35
     bumi
    2.18
     tierra
    2.14
     Tierra
    2.11
    Activations Density 0.015%

    No Known Activations