© 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. 40283
    Prev
    Next
    INDEX
    Explanations

    credit, credit check, credit card

    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
    ’
    0.86
    '
    0.85
    !
    0.82
    ้
    0.81
    ิ
    0.79
    0.76
    ion
    0.76
    ся
    0.73
     was
    0.73
    .
    0.72
    POSITIVE LOGITS
     credit
    0.93
    Credit
    0.93
     креди
    0.85
    CRED
    0.85
     Credit
    0.84
     crédito
    0.82
    Cred
    0.81
     CREDIT
    0.80
     kred
    0.79
    credit
    0.79
    Activations Density 0.013%

    No Known Activations