© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7180
    Prev
    Next
    INDEX
    Explanations

    **a** followed by a noun phrase

    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_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
     egregious
    0.59
    Truck
    0.55
     laboratorio
    0.54
     laborers
    0.53
     truck
    0.51
     similit
    0.51
     skillet
    0.50
    愚
    0.50
    Federal
    0.49
    Labor
    0.48
    POSITIVE LOGITS
     postcode
    0.75
     carers
    0.61
     adverts
    0.59
     unrivalled
    0.59
     colourful
    0.57
     envisaged
    0.56
     slimming
    0.55
     banknotes
    0.54
     carer
    0.54
     NHS
    0.52
    Activations Density 0.043%

    No Known Activations