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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 20255
    Prev
    Next
    INDEX
    Explanations

    hiding or concealing information

    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_65k_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
    z
    0.47
    伌
    0.45
    zeg
    0.45
     silla
    0.43
     validations
    0.43
    kon
    0.42
    közi
    0.42
    穰
    0.41
    鎭
    0.41
    の人
    0.40
    POSITIVE LOGITS
     hide
    1.44
     hiding
    1.35
     Hide
    1.25
    Hide
    1.19
     concealment
    1.16
     hides
    1.16
     esconder
    1.15
     hid
    1.14
    hide
    1.13
     concealing
    1.13
    Activations Density 0.118%

    No Known Activations