© 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. 125292
    Prev
    Next
    INDEX
    Explanations

    self-harm and suicidal thoughts

    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
    Jos
    0.45
     коре
    0.45
     bolder
    0.44
     Antoinette
    0.44
    ᱠ
    0.43
     corset
    0.43
     Kore
    0.42
     मॅ
    0.42
    美食
    0.41
    観察
    0.41
    POSITIVE LOGITS
     Devices
    0.58
     realizing
    0.47
     devices
    0.46
    Devices
    0.44
    devices
    0.43
     kicking
    0.42
     feste
    0.42
     Pharmacology
    0.42
    跷
    0.42
     effettuare
    0.41
    Activations Density 0.005%

    No Known Activations