© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 124869
    Prev
    Next
    INDEX
    Explanations

    foreign words and phrases

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

    Utilitarianism maximize happiness

    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_31_width_262k_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
     ভ্রমণের
    0.55
    াবলীর
    0.46
     elevates
    0.44
     ভ্রমণ
    0.43
     ヘ
    0.42
     encanta
    0.42
    Hiking
    0.42
    WriteStream
    0.42
    おり
    0.42
     CGRectMake
    0.41
    POSITIVE LOGITS
    isas
    0.45
     Les
    0.44
    ações
    0.43
    iret
    0.43
    ANGO
    0.43
    isa
    0.42
    ]
    0.42
    avec
    0.42
    ovsky
    0.42
    legi
    0.42
    Activations Density 0.003%

    No Known Activations