© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 1204
    Prev
    Next
    INDEX
    Explanations

    AI concepts and programming

    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
    kwik
    1.25
    跚
    1.16
     eventdata
    1.10
    ILLIPS
    1.10
    kelijk
    1.10
     kej
    1.09
    い
    1.09
    Dynamics
    1.09
    enek
    1.08
    лений
    1.04
    POSITIVE LOGITS
    rt
    1.74
    rer
    1.64
    erc
    1.64
    ERC
    1.64
    ρ
    1.63
    erg
    1.61
    eri
    1.59
    rd
    1.58
    р
    1.58
    ert
    1.57
    Activations Density 0.583%

    No Known Activations