© 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. 7449
    Prev
    Next
    INDEX
    Explanations

    in essence, in summary

    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
     convuls
    1.28
     sobbing
    1.22
     delir
    1.21
    <unused2041>
    1.20
     preoccup
    1.20
    踟
    1.18
    ляется
    1.18
    ]|
    1.17
     animé
    1.17
     reluctance
    1.16
    POSITIVE LOGITS
     aswell
    2.43
     adicional
    2.23
     overall
    2.11
     also
    2.11
     additionally
    1.99
    overall
    1.99
     besides
    1.87
    total
    1.87
    also
    1.86
     Overall
    1.82
    Activations Density 0.082%

    No Known Activations