© 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. 3416
    Prev
    Next
    INDEX
    Explanations

    Usually comes in types

    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
     envis
    1.38
    uldig
    1.31
     Roadmap
    1.29
    が進
    1.28
     accompagner
    1.27
     Rund
    1.26
     appoints
    1.26
    縝
    1.26
     Encyclopædia
    1.26
    kowego
    1.25
    POSITIVE LOGITS
     fraction
    1.49
     fractions
    1.42
     mixture
    1.33
     equivalence
    1.25
    mixture
    1.25
    fraction
    1.24
     mixed
    1.22
     mixtures
    1.17
    Hector
    1.15
     Hector
    1.11
    Activations Density 0.068%

    No Known Activations