© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 3524
    Prev
    Next
    INDEX
    Explanations

    cold followed by dread

    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_16_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
    ים
    1.06
    도
    1.04
    ה
    0.96
    ות
    0.95
    も
    0.95
    ک
    0.91
    ла
    0.91
    리
    0.90
    נו
    0.88
    茷
    0.87
    POSITIVE LOGITS
     frío
    1.52
    Cold
    1.38
     frio
    1.38
    cold
    1.32
     cold
    1.27
    冷
    1.18
     colder
    1.13
     Cold
    1.12
     soğ
    1.11
    AY
    1.05
    Activations Density 0.026%

    No Known Activations