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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 101382
    Prev
    Next
    INDEX
    Explanations

    core ethical arguments

    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_31_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
     distortions
    0.52
     distort
    0.49
     bars
    0.46
     inversion
    0.46
     prices
    0.45
     density
    0.44
    ة
    0.44
     cheap
    0.43
     eff
    0.42
     pol
    0.42
    POSITIVE LOGITS
    achtige
    0.55
    boldsymbol
    0.53
    }%
    0.52
     байланы
    0.51
    ᅡ
    0.51
     Kindern
    0.50
    érer
    0.50
     pâte
    0.50
    ambilan
    0.49
    jarige
    0.49
    Activations Density 0.003%

    No Known Activations