© 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. 1621
    Prev
    Next
    INDEX
    Explanations

    numbers and scales

    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
     nourrice
    1.25
    bola
    1.21
    粱
    1.15
    psons
    1.13
    '!
    1.09
     unes
    1.08
     instruções
    1.07
     cramps
    1.06
     negroes
    1.05
    ผู้ชมในสนาม
    1.05
    POSITIVE LOGITS
    7
    1.98
    8
    1.97
    2
    1.94
    9
    1.87
    6
    1.85
    5
    1.80
    4
    1.65
    3
    1.64
     trillion
    1.52
    1
    1.38
    Activations Density 0.121%

    No Known Activations