© 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. 3397
    Prev
    Next
    INDEX
    Explanations

    CPU and instructions

    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
     Mér
    1.38
    BOR
    1.37
    μί
    1.28
     tehát
    1.23
     foreclose
    1.22
     exclusively
    1.17
     umjet
    1.15
    을
    1.15
     şek
    1.14
     pluripotent
    1.13
    POSITIVE LOGITS
     tougher
    1.71
    junior
    1.65
     younger
    1.55
     junior
    1.54
    Junior
    1.53
    afone
    1.49
     toughest
    1.46
     sportswear
    1.45
     nephew
    1.45
     miner
    1.44
    Activations Density 0.015%

    No Known Activations