© 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. 51220
    Prev
    Next
    INDEX
    Explanations

    negative concepts and food items

    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
    t
    0.47
    ustainable
    0.44
    acceler
    0.44
    incinn
    0.43
    abilit
    0.42
    ፈጥ
    0.41
    escap
    0.40
    ized
    0.40
    ă
    0.40
    champion
    0.40
    POSITIVE LOGITS
     dui
    0.55
     soprano
    0.51
     zatim
    0.49
     vilket
    0.49
     semelhante
    0.48
     Picasso
    0.48
     porcine
    0.48
     cuja
    0.48
     tiennent
    0.48
     LA
    0.47
    Activations Density 0.004%

    No Known Activations