© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 132404
    Prev
    Next
    INDEX
    Explanations

    well-being, safety, rights, suffering

    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_40_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
    typescript
    0.40
    ின்
    0.39
    your
    0.38
    ichloro
    0.38
    ിലെ
    0.38
     remarkable
    0.37
     Sprague
    0.37
    텃
    0.37
     your
    0.36
    rafa
    0.36
    POSITIVE LOGITS
     welfare
    0.92
     plight
    0.90
     needs
    0.89
     wellbeing
    0.88
     Bedürfnisse
    0.87
     happiness
    0.86
     benessere
    0.84
     bienestar
    0.83
    Needs
    0.82
     sufferings
    0.82
    Activations Density 0.033%

    No Known Activations