Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 6788
    Prev
    Next
    INDEX
    Explanations

    `"use strict";`

    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_40_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
     دل
    0.46
    श्ती
    0.41
     lĩnh
    0.41
     قوس
    0.40
    衩
    0.39
    coprotein
    0.38
     haies
    0.38
     hatchery
    0.38
     செல்சியஸ்
    0.38
    𝓽
    0.37
    POSITIVE LOGITS
     strict
    1.55
     Strict
    1.39
    strict
    1.30
     stricter
    1.30
    Strict
    1.28
    严格
    1.19
    厳
    1.16
     strictest
    1.13
    严
    1.13
    StrictMode
    1.10
    Activations Density 0.004%

    No Known Activations