© 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. 50997
    Prev
    Next
    INDEX
    Explanations

    propaganda and deception

    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
    ంత
    0.47
    ле
    0.46
    :
    0.46
    ළු
    0.45
     pensé
    0.43
    :>
    0.42
    ྷ
    0.41
    权利
    0.41
    స
    0.40
    ය
    0.40
    POSITIVE LOGITS
    accom
    0.52
     पीले
    0.49
     તેને
    0.48
     Є
    0.47
    irti
    0.47
     Еў
    0.46
     Tattha
    0.46
    esperienza
    0.44
    enchen
    0.44
    žem
    0.44
    Activations Density 0.000%

    No Known Activations