© 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-262K
    7. 25227
    Prev
    Next
    INDEX
    Explanations

    pronouns introducing descriptions

    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
    ക്കാരി
    0.47
    경제
    0.44
     বৎ
    0.41
    Institute
    0.41
    ваясь
    0.40
    career
    0.40
    සා
    0.39
    ǽ
    0.39
    हाबाद
    0.39
    ర్కొ
    0.39
    POSITIVE LOGITS
     died
    0.50
     is
    0.49
     smells
    0.48
     upcoming
    0.46
     recently
    0.45
     reste
    0.45
     Docker
    0.45
     ruined
    0.44
     Temperatur
    0.44
     recieved
    0.44
    Activations Density 0.007%

    No Known Activations