© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 13558
    Prev
    Next
    INDEX
    Explanations

    inspiration and influence

    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
     niezb
    0.39
     solicitor
    0.39
    agati
    0.38
    c
    0.38
     defamatory
    0.38
    fc
    0.37
     accurately
    0.36
     সন্দেহ
    0.35
     delicately
    0.35
    п
    0.35
    POSITIVE LOGITS
     inspiration
    1.59
     Inspiration
    1.39
     inspirations
    1.37
     inspir
    1.34
    inspiration
    1.33
     inspire
    1.29
     inspiración
    1.28
     вдох
    1.24
    inspir
    1.23
     ispir
    1.16
    Activations Density 0.163%

    No Known Activations