© 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. 64602
    Prev
    Next
    INDEX
    Explanations

    harm, threats, distress

    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
    ៦
    0.49
     சிறப்பாக
    0.49
    ចប់
    0.47
    icioso
    0.45
     சின்னமாக
    0.44
     માત્ર
    0.44
     লিও
    0.44
     студен
    0.44
    旁邊
    0.44
    Kiza
    0.43
    POSITIVE LOGITS
     aforementioned
    0.46
    사
    0.46
     loopholes
    0.43
     reconc
    0.42
     booze
    0.41
     juggle
    0.40
     sanctions
    0.40
     laminate
    0.40
     collectively
    0.38
     roadmap
    0.38
    Activations Density 0.023%

    No Known Activations