© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4760
    Prev
    Next
    INDEX
    Explanations

    required assistance, role, issue, component

    np_acts-logits-general · gemini-2.5-flash-lite

    unwanted sexual thoughts or urges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ty
    0.40
    '...
    0.40
    ...'
    0.39
    ,​
    0.38
    =',
    0.38
    :...
    0.38
     ​
    0.37
    Hero
    0.37
     Hero
    0.36
     superposition
    0.36
    POSITIVE LOGITS
    etano
    0.42
    acées
    0.41
    acée
    0.39
    atini
    0.38
    adai
    0.38
     Kal
    0.38
    Kal
    0.38
    escent
    0.38
    **:
    0.37
    ሞች
    0.36
    Activations Density 0.005%

    No Known Activations