© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 654
    Prev
    Next
    INDEX
    Explanations

    digital signatures and cryptography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_16k_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
     skincare
    0.96
     mindfulness
    0.89
    撣
    0.86
     영화
    0.86
     vaping
    0.85
     firefighting
    0.85
     탐
    0.82
     sagging
    0.82
    褒
    0.81
     VFX
    0.80
    POSITIVE LOGITS
     crypt
    1.16
     primes
    1.12
     prime
    1.12
     elliptic
    1.11
     cryptographic
    1.11
    密钥
    1.05
     cryptography
    1.05
     क्रिप्ट
    1.04
     moduli
    1.03
     modulus
    1.03
    Activations Density 0.737%

    No Known Activations