© 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. 4423
    Prev
    Next
    INDEX
    Explanations

    decipher words and text

    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
    적인
    1.64
    iset
    1.48
    様子
    1.47
     aces
    1.45
    worms
    1.45
    檚
    1.42
    ily
    1.42
    적
    1.40
    ไหล
    1.39
    iglia
    1.38
    POSITIVE LOGITS
    outube
    3.07
    yyyyyyyy
    2.45
    ELLOW
    2.39
    kjav
    2.37
    rinth
    2.23
    ahuasca
    2.13
     newTask
    2.12
    apons
    2.10
    OMX
    2.10
    ancha
    2.10
    Activations Density 0.120%

    No Known Activations