© 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. 365
    Prev
    Next
    INDEX
    Explanations

    MAC addresses and typical consideration

    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
    NELL
    2.10
    yled
    1.95
    偕
    1.93
     both
    1.89
    eing
    1.88
     evidence
    1.87
     entrambi
    1.86
    yiz
    1.85
    imonials
    1.81
     period
    1.81
    POSITIVE LOGITS
    ειτουργ
    2.43
    ambda
    2.32
    MNOP
    2.18
    츠
    2.18
    Classes
    2.16
    thickness
    2.15
    ifestyle
    2.15
    mnopqr
    2.13
    7
    2.12
    ifting
    2.11
    Activations Density 0.278%

    No Known Activations