© 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. 979
    Prev
    Next
    INDEX
    Explanations

    minecraft is

    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
    šit
    1.31
    ้ม
    1.25
     voller
    1.19
     disampaikan
    1.18
    她在
    1.17
    缀
    1.15
    ributed
    1.14
     adjourn
    1.13
    dler
    1.12
    fixes
    1.10
    POSITIVE LOGITS
    7
    2.15
    esque
    2.14
    ovich
    2.11
     Quadr
    2.10
    8
    2.09
    ianos
    2.09
    ovsk
    2.00
    4
    1.95
    6
    1.93
     schwarzen
    1.91
    Activations Density 0.375%

    No Known Activations