© 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. 58209
    Prev
    Next
    INDEX
    Explanations

    dance pieces, expert therapist, be pampered

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

    body, pain, skin conditions

    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
    ]
    0.54
    nson
    0.47
    "
    0.46
    𝗦
    0.45
    REPORT
    0.44
    ೬
    0.44
    john
    0.43
    Outline
    0.42
     avaient
    0.41
    튼
    0.41
    POSITIVE LOGITS
     exhilar
    0.49
     gliding
    0.48
     Heterocycl
    0.47
     பார்க்கலாம்
    0.47
    体验
    0.46
     immersing
    0.46
    反而
    0.45
     adrenalin
    0.44
     Kombination
    0.43
     ఉంటుంది
    0.43
    Activations Density 0.000%

    No Known Activations