Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 43690
    Prev
    Next
    INDEX
    Explanations

    negative contrasting phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     га
    0.47
     Galaxy
    0.46
     \
    0.45
     Iris
    0.44
     Motion
    0.44
    ippings
    0.44
     inertia
    0.42
     resistive
    0.42
    ة
    0.42
     Inert
    0.42
    POSITIVE LOGITS
    ambiental
    0.48
    years
    0.48
     ಅನೇಕ
    0.44
    tiene
    0.44
    org
    0.43
    affiliated
    0.43
    belum
    0.43
    arb
    0.42
    ತಿಯ
    0.42
    ದಾರ
    0.42
    Activations Density 0.004%

    No Known Activations