© 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-16K
    7. 1000
    Prev
    Next
    INDEX
    Explanations

    latex \usepackage

    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_16k_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
    chats
    1.51
    die
    1.49
    dst
    1.42
    ementia
    1.41
    ï
    1.36
    chat
    1.35
    Sing
    1.35
    լ
    1.35
    dense
    1.34
     Beautiful
    1.34
    POSITIVE LOGITS
    urre
    1.55
    UVW
    1.51
    oryt
    1.50
    ovací
    1.47
    顰
    1.46
    abhut
    1.45
    ropole
    1.44
    masht
    1.44
    adihi
    1.43
    ytu
    1.42
    Activations Density 0.016%

    No Known Activations