© 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-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3603
    Prev
    Next
    INDEX
    Explanations

    high/temperatures followed by potential/can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reagents
    2.25
     astronomers
    2.20
     momenta
    2.16
     dosimetry
    2.14
     forecasts
    2.12
     adduced
    2.12
     料
    2.10
     diagnoses
    2.08
    hoea
    2.08
    ources
    2.08
    POSITIVE LOGITS
     Single
    2.24
    Discrete
    2.20
    hybrid
    2.20
    Hybrid
    2.18
     Dual
    2.17
     Hybrid
    2.16
     Traditional
    2.16
     Semi
    2.16
     Direct
    2.14
    7
    2.08
    Activations Density 1.362%

    No Known Activations